[
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-03T17:02:55.360Z",
    "tokens": {
      "promptTokens": 2137,
      "completionTokens": 8344,
      "totalTokens": 10481
    },
    "costUsd": 0.43857,
    "durationMs": 93382,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 1,
    "improvement": 0.1428571428571429,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8571428571428571,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.95,
    "updatedAt": "2026-09-03T17:03:48.863Z",
    "tokens": {
      "promptTokens": 194,
      "completionTokens": 18551,
      "totalTokens": 18745
    },
    "costUsd": 0.92949,
    "durationMs": 174385,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.8388888888888889,
    "improvement": -0.11111111111111105,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Android",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:03:03.914Z",
    "tokens": {
      "promptTokens": 99,
      "completionTokens": 12096,
      "totalTokens": 12195
    },
    "costUsd": 0.60579,
    "durationMs": 117058,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:01:49.542Z",
    "tokens": {
      "promptTokens": 1794,
      "completionTokens": 2428,
      "totalTokens": 4222
    },
    "costUsd": 0.13934,
    "durationMs": 40600,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:59:29.367Z",
    "tokens": {
      "promptTokens": 371,
      "completionTokens": 1091,
      "totalTokens": 1462
    },
    "costUsd": 0.05826,
    "durationMs": 14940,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9327777777777777,
    "updatedAt": "2026-09-03T16:59:37.088Z",
    "tokens": {
      "promptTokens": 296,
      "completionTokens": 3068,
      "totalTokens": 3364
    },
    "costUsd": 0.15636,
    "durationMs": 33487,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9777777777777779,
    "improvement": 0.04500000000000015,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9777777777777779,
    "skillsImprovement": 0.04500000000000015,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-03T17:02:29.142Z",
    "tokens": {
      "promptTokens": 354,
      "completionTokens": 13621,
      "totalTokens": 13975
    },
    "costUsd": 0.68459,
    "durationMs": 131400,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0.01666666666666672,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.85,
    "skillsImprovement": -0.050000000000000044,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8917748917748919,
    "updatedAt": "2026-09-03T17:00:06.619Z",
    "tokens": {
      "promptTokens": 371,
      "completionTokens": 1381,
      "totalTokens": 1752
    },
    "costUsd": 0.07276,
    "durationMs": 24731,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8614718614718614,
    "improvement": -0.030303030303030498,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8787878787878788,
    "skillsImprovement": -0.012987012987013102,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8756185335132703,
    "updatedAt": "2026-09-03T16:59:43.987Z",
    "tokens": {
      "promptTokens": 305,
      "completionTokens": 3816,
      "totalTokens": 4121
    },
    "costUsd": 0.19385,
    "durationMs": 52495,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": -0.002136752136752129,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8478407557354926,
    "skillsImprovement": -0.02777777777777779,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8318181818181818,
    "updatedAt": "2026-09-03T17:00:54.332Z",
    "tokens": {
      "promptTokens": 170,
      "completionTokens": 6692,
      "totalTokens": 6862
    },
    "costUsd": 0.3363,
    "durationMs": 77068,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8522727272727273,
    "improvement": 0.020454545454545503,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7818181818181819,
    "skillsImprovement": -0.04999999999999993,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:00:07.074Z",
    "tokens": {
      "promptTokens": 424,
      "completionTokens": 4340,
      "totalTokens": 4764
    },
    "costUsd": 0.22124,
    "durationMs": 49714,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8171717171717172,
    "updatedAt": "2026-09-03T17:00:36.186Z",
    "tokens": {
      "promptTokens": 329,
      "completionTokens": 2459,
      "totalTokens": 2788
    },
    "costUsd": 0.12624,
    "durationMs": 29425,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8782828282828282,
    "improvement": 0.061111111111111005,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.6782828282828284,
    "skillsImprovement": -0.13888888888888884,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:01:50.215Z",
    "tokens": {
      "promptTokens": 1969,
      "completionTokens": 2425,
      "totalTokens": 4394
    },
    "costUsd": 0.14094,
    "durationMs": 34207,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-03T16:59:12.603Z",
    "tokens": {
      "promptTokens": 2144,
      "completionTokens": 1432,
      "totalTokens": 3576
    },
    "costUsd": 0.09304,
    "durationMs": 20800,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8235294117647058,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.6666666666666666,
    "updatedAt": "2026-09-03T17:02:34.628Z",
    "tokens": {
      "promptTokens": 1739,
      "completionTokens": 3855,
      "totalTokens": 5594
    },
    "costUsd": 0.21014,
    "durationMs": 44893,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.33333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.75,
    "updatedAt": "2026-09-03T17:02:28.247Z",
    "tokens": {
      "promptTokens": 184,
      "completionTokens": 10920,
      "totalTokens": 11104
    },
    "costUsd": 0.54784,
    "durationMs": 106933,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": -0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.25,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-fable-5-1",
    "label": "Claude Fable 5.1",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:02:27.176Z",
    "tokens": {
      "promptTokens": 94,
      "completionTokens": 10391,
      "totalTokens": 10485
    },
    "costUsd": 0.52049,
    "durationMs": 101503,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-03T17:06:20.036Z",
    "tokens": {
      "promptTokens": 2135,
      "completionTokens": 12789,
      "totalTokens": 14924
    },
    "costUsd": 0.6608,
    "durationMs": 124476,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8571428571428571,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.8388888888888889,
    "updatedAt": "2026-09-03T17:05:57.671Z",
    "tokens": {
      "promptTokens": 192,
      "completionTokens": 14249,
      "totalTokens": 14441
    },
    "costUsd": 0.71437,
    "durationMs": 127151,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.95,
    "improvement": 0.11111111111111105,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9,
    "skillsImprovement": 0.061111111111111116,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:04:54.963Z",
    "tokens": {
      "promptTokens": 97,
      "completionTokens": 6537,
      "totalTokens": 6634
    },
    "costUsd": 0.32782,
    "durationMs": 62764,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:04:39.695Z",
    "tokens": {
      "promptTokens": 1792,
      "completionTokens": 2759,
      "totalTokens": 4551
    },
    "costUsd": 0.15587,
    "durationMs": 41485,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:02:55.422Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 803,
      "totalTokens": 1172
    },
    "costUsd": 0.04384,
    "durationMs": 11733,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9555555555555555,
    "updatedAt": "2026-09-03T17:02:45.331Z",
    "tokens": {
      "promptTokens": 294,
      "completionTokens": 1368,
      "totalTokens": 1662
    },
    "costUsd": 0.07134,
    "durationMs": 16046,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9777777777777779,
    "improvement": 0.022222222222222365,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333332,
    "skillsImprovement": -0.022222222222222254,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8833333333333334,
    "updatedAt": "2026-09-03T17:04:26.494Z",
    "tokens": {
      "promptTokens": 352,
      "completionTokens": 5929,
      "totalTokens": 6281
    },
    "costUsd": 0.29997,
    "durationMs": 59253,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8666666666666666,
    "improvement": -0.01666666666666683,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333333,
    "skillsImprovement": 0.04999999999999993,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-03T17:03:23.671Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 1369,
      "totalTokens": 1738
    },
    "costUsd": 0.07214,
    "durationMs": 24784,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9393939393939394,
    "improvement": 0.07792207792207806,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8614718614718614,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8478407557354926,
    "updatedAt": "2026-09-03T17:02:59.639Z",
    "tokens": {
      "promptTokens": 303,
      "completionTokens": 2362,
      "totalTokens": 2665
    },
    "costUsd": 0.12113,
    "durationMs": 46121,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": 0.02564102564102566,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8478407557354926,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8068181818181819,
    "updatedAt": "2026-09-03T17:03:42.750Z",
    "tokens": {
      "promptTokens": 168,
      "completionTokens": 2881,
      "totalTokens": 3049
    },
    "costUsd": 0.14573,
    "durationMs": 47105,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8545454545454545,
    "improvement": 0.04772727272727262,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7772727272727272,
    "skillsImprovement": -0.029545454545454652,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:03:14.905Z",
    "tokens": {
      "promptTokens": 422,
      "completionTokens": 2430,
      "totalTokens": 2852
    },
    "costUsd": 0.12572,
    "durationMs": 29425,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7893939393939394,
    "updatedAt": "2026-09-03T17:03:30.751Z",
    "tokens": {
      "promptTokens": 327,
      "completionTokens": 1201,
      "totalTokens": 1528
    },
    "costUsd": 0.06332,
    "durationMs": 16900,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.594949494949495,
    "improvement": -0.19444444444444442,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8227272727272728,
    "skillsImprovement": 0.033333333333333326,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:04:55.164Z",
    "tokens": {
      "promptTokens": 1967,
      "completionTokens": 2547,
      "totalTokens": 4514
    },
    "costUsd": 0.14702,
    "durationMs": 43072,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.9,
    "improvement": -0.09999999999999998,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-03T17:02:38.240Z",
    "tokens": {
      "promptTokens": 2142,
      "completionTokens": 1245,
      "totalTokens": 3387
    },
    "costUsd": 0.08367,
    "durationMs": 16748,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.7647058823529411,
    "improvement": -0.05882352941176472,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:05:03.535Z",
    "tokens": {
      "promptTokens": 1737,
      "completionTokens": 3119,
      "totalTokens": 4856
    },
    "costUsd": 0.17332,
    "durationMs": 36908,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.16666666666666663,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333333,
    "updatedAt": "2026-09-03T17:04:47.748Z",
    "tokens": {
      "promptTokens": 182,
      "completionTokens": 6803,
      "totalTokens": 6985
    },
    "costUsd": 0.34197,
    "durationMs": 63968,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.41666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-fable-5",
    "label": "Claude Fable 5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:05:09.356Z",
    "tokens": {
      "promptTokens": 92,
      "completionTokens": 8805,
      "totalTokens": 8897
    },
    "costUsd": 0.44117,
    "durationMs": 83759,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:39.559Z",
    "tokens": {
      "promptTokens": 2137,
      "completionTokens": 4676,
      "totalTokens": 6813
    },
    "costUsd": 0.102068,
    "durationMs": 39887,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.95,
    "updatedAt": "2026-09-28T20:34:07.065Z",
    "tokens": {
      "promptTokens": 194,
      "completionTokens": 15007,
      "totalTokens": 15201
    },
    "costUsd": 0.300916,
    "durationMs": 113380,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 1,
    "improvement": 0.050000000000000044,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.050000000000000044,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:38.819Z",
    "tokens": {
      "promptTokens": 99,
      "completionTokens": 9031,
      "totalTokens": 9130
    },
    "costUsd": 0.181016,
    "durationMs": 71735,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:11.364Z",
    "tokens": {
      "promptTokens": 1794,
      "completionTokens": 1943,
      "totalTokens": 3737
    },
    "costUsd": 0.046036,
    "durationMs": 26446,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": -0.09090909090909094,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:29:16.752Z",
    "tokens": {
      "promptTokens": 371,
      "completionTokens": 900,
      "totalTokens": 1271
    },
    "costUsd": 0.019484,
    "durationMs": 9014,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9527777777777778,
    "updatedAt": "2026-09-28T20:29:07.347Z",
    "tokens": {
      "promptTokens": 296,
      "completionTokens": 1494,
      "totalTokens": 1790
    },
    "costUsd": 0.031064,
    "durationMs": 14727,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9527777777777778,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9577777777777777,
    "skillsImprovement": 0.004999999999999893,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8466666666666667,
    "updatedAt": "2026-09-28T20:31:56.281Z",
    "tokens": {
      "promptTokens": 354,
      "completionTokens": 8271,
      "totalTokens": 8625
    },
    "costUsd": 0.166836,
    "durationMs": 63891,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9333333333333333,
    "improvement": 0.08666666666666667,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8833333333333334,
    "skillsImprovement": 0.036666666666666736,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779222,
    "updatedAt": "2026-09-28T20:30:24.687Z",
    "tokens": {
      "promptTokens": 371,
      "completionTokens": 1196,
      "totalTokens": 1567
    },
    "costUsd": 0.025404,
    "durationMs": 16016,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9220779220779222,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9393939393939394,
    "skillsImprovement": 0.017316017316017285,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.9012595591542959,
    "updatedAt": "2026-09-28T20:28:52.242Z",
    "tokens": {
      "promptTokens": 305,
      "completionTokens": 3453,
      "totalTokens": 3758
    },
    "costUsd": 0.07028,
    "durationMs": 37452,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8756185335132703,
    "improvement": -0.02564102564102555,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8756185335132703,
    "skillsImprovement": -0.02564102564102555,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8090909090909091,
    "updatedAt": "2026-09-28T20:30:33.439Z",
    "tokens": {
      "promptTokens": 170,
      "completionTokens": 4461,
      "totalTokens": 4631
    },
    "costUsd": 0.0899,
    "durationMs": 42845,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8295454545454546,
    "improvement": 0.020454545454545503,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8772727272727272,
    "skillsImprovement": 0.06818181818181812,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-28T20:29:50.194Z",
    "tokens": {
      "promptTokens": 424,
      "completionTokens": 3453,
      "totalTokens": 3877
    },
    "costUsd": 0.070756,
    "durationMs": 36579,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7696969696969697,
    "updatedAt": "2026-09-28T20:30:45.354Z",
    "tokens": {
      "promptTokens": 329,
      "completionTokens": 1137,
      "totalTokens": 1466
    },
    "costUsd": 0.024056,
    "durationMs": 11525,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7616161616161617,
    "improvement": -0.00808080808080791,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8171717171717172,
    "skillsImprovement": 0.04747474747474756,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:16.316Z",
    "tokens": {
      "promptTokens": 1969,
      "completionTokens": 2172,
      "totalTokens": 4141
    },
    "costUsd": 0.051316,
    "durationMs": 20886,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-28T20:28:49.650Z",
    "tokens": {
      "promptTokens": 2144,
      "completionTokens": 1259,
      "totalTokens": 3403
    },
    "costUsd": 0.033756,
    "durationMs": 12211,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8235294117647058,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-28T20:33:45.051Z",
    "tokens": {
      "promptTokens": 1739,
      "completionTokens": 3082,
      "totalTokens": 4821
    },
    "costUsd": 0.068596,
    "durationMs": 33290,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.5,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.33333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.75,
    "updatedAt": "2026-09-28T20:32:44.510Z",
    "tokens": {
      "promptTokens": 184,
      "completionTokens": 7835,
      "totalTokens": 8019
    },
    "costUsd": 0.157436,
    "durationMs": 62212,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.16666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-opus-5-5",
    "label": "Claude Opus 5.5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:32:55.028Z",
    "tokens": {
      "promptTokens": 94,
      "completionTokens": 7262,
      "totalTokens": 7356
    },
    "costUsd": 0.145616,
    "durationMs": 58349,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-03T17:11:03.625Z",
    "tokens": {
      "promptTokens": 2135,
      "completionTokens": 15659,
      "totalTokens": 17794
    },
    "costUsd": 0.40215,
    "durationMs": 156449,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8571428571428571,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.8944444444444444,
    "updatedAt": "2026-09-03T17:15:54.227Z",
    "tokens": {
      "promptTokens": 192,
      "completionTokens": 23490,
      "totalTokens": 23682
    },
    "costUsd": 0.58821,
    "durationMs": 521337,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.788888888888889,
    "improvement": -0.1055555555555554,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.788888888888889,
    "skillsImprovement": -0.1055555555555554,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Android",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:10:24.347Z",
    "tokens": {
      "promptTokens": 97,
      "completionTokens": 19389,
      "totalTokens": 19486
    },
    "costUsd": 0.48521,
    "durationMs": 187021,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:08:27.381Z",
    "tokens": {
      "promptTokens": 1792,
      "completionTokens": 2826,
      "totalTokens": 4618
    },
    "costUsd": 0.07961,
    "durationMs": 40372,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:05:42.894Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 2214,
      "totalTokens": 2583
    },
    "costUsd": 0.057195,
    "durationMs": 25469,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9105555555555555,
    "updatedAt": "2026-09-03T17:05:23.545Z",
    "tokens": {
      "promptTokens": 294,
      "completionTokens": 1753,
      "totalTokens": 2047
    },
    "costUsd": 0.045295,
    "durationMs": 19886,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9355555555555555,
    "improvement": 0.025000000000000022,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9327777777777777,
    "skillsImprovement": 0.022222222222222254,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8666666666666668,
    "updatedAt": "2026-09-03T17:09:03.989Z",
    "tokens": {
      "promptTokens": 352,
      "completionTokens": 17155,
      "totalTokens": 17507
    },
    "costUsd": 0.430635,
    "durationMs": 159215,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8666666666666666,
    "improvement": -2.220446049250313e-16,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8833333333333334,
    "skillsImprovement": 0.016666666666666607,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779222,
    "updatedAt": "2026-09-03T17:06:13.173Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 1505,
      "totalTokens": 1874
    },
    "costUsd": 0.03947,
    "durationMs": 23927,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9523809523809524,
    "improvement": 0.030303030303030276,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8917748917748919,
    "skillsImprovement": -0.030303030303030276,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8734817813765182,
    "updatedAt": "2026-09-03T17:05:49.103Z",
    "tokens": {
      "promptTokens": 303,
      "completionTokens": 4870,
      "totalTokens": 5173
    },
    "costUsd": 0.123265,
    "durationMs": 61232,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8478407557354926,
    "improvement": -0.02564102564102566,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.02777777777777768,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8772727272727272,
    "updatedAt": "2026-09-03T17:07:17.185Z",
    "tokens": {
      "promptTokens": 168,
      "completionTokens": 8198,
      "totalTokens": 8366
    },
    "costUsd": 0.20579,
    "durationMs": 94134,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.9249999999999999,
    "improvement": 0.04772727272727273,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.9045454545454545,
    "skillsImprovement": 0.027272727272727337,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:06:17.071Z",
    "tokens": {
      "promptTokens": 422,
      "completionTokens": 5025,
      "totalTokens": 5447
    },
    "costUsd": 0.127735,
    "durationMs": 53423,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7838383838383839,
    "updatedAt": "2026-09-03T17:06:35.842Z",
    "tokens": {
      "promptTokens": 327,
      "completionTokens": 1576,
      "totalTokens": 1903
    },
    "costUsd": 0.041035,
    "durationMs": 18587,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7893939393939394,
    "improvement": 0.005555555555555536,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.7893939393939394,
    "skillsImprovement": 0.005555555555555536,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:08:33.489Z",
    "tokens": {
      "promptTokens": 1967,
      "completionTokens": 2982,
      "totalTokens": 4949
    },
    "costUsd": 0.084385,
    "durationMs": 34279,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:05:17.301Z",
    "tokens": {
      "promptTokens": 2142,
      "completionTokens": 2393,
      "totalTokens": 4535
    },
    "costUsd": 0.070535,
    "durationMs": 23842,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.7647058823529411,
    "improvement": -0.23529411764705888,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": -0.17647058823529416,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:09:40.090Z",
    "tokens": {
      "promptTokens": 1737,
      "completionTokens": 6264,
      "totalTokens": 8001
    },
    "costUsd": 0.165285,
    "durationMs": 72578,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.16666666666666663,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.8333333333333333,
    "updatedAt": "2026-09-03T18:11:31.042Z",
    "tokens": {
      "promptTokens": 182,
      "completionTokens": 26702,
      "totalTokens": 26884
    },
    "durationMs": 256052,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": -0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.16666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-opus-5",
    "label": "Claude Opus 5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:09:35.945Z",
    "tokens": {
      "promptTokens": 92,
      "completionTokens": 15304,
      "totalTokens": 15396
    },
    "costUsd": 0.38306,
    "durationMs": 146526,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-03T17:12:50.384Z",
    "tokens": {
      "promptTokens": 2135,
      "completionTokens": 6893,
      "totalTokens": 9028
    },
    "costUsd": 0.0732,
    "durationMs": 63074,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0.1428571428571428,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7142857142857143,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.7277777777777779,
    "updatedAt": "2026-09-03T17:14:09.220Z",
    "tokens": {
      "promptTokens": 192,
      "completionTokens": 23879,
      "totalTokens": 24071
    },
    "costUsd": 0.239174,
    "durationMs": 185436,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.6833333333333333,
    "improvement": -0.04444444444444451,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.8388888888888889,
    "skillsImprovement": 0.11111111111111105,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:12:13.388Z",
    "tokens": {
      "promptTokens": 97,
      "completionTokens": 6793,
      "totalTokens": 6890
    },
    "costUsd": 0.068124,
    "durationMs": 55561,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.8181818181818182,
    "updatedAt": "2026-09-03T17:11:56.472Z",
    "tokens": {
      "promptTokens": 1792,
      "completionTokens": 2167,
      "totalTokens": 3959
    },
    "costUsd": 0.025254,
    "durationMs": 32581,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0.18181818181818177,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8181818181818182,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:09:50.311Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 408,
      "totalTokens": 777
    },
    "costUsd": 0.004818,
    "durationMs": 6147,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9305555555555556,
    "updatedAt": "2026-09-03T17:09:49.544Z",
    "tokens": {
      "promptTokens": 294,
      "completionTokens": 1377,
      "totalTokens": 1671
    },
    "costUsd": 0.014358,
    "durationMs": 12111,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9527777777777778,
    "improvement": 0.022222222222222254,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9105555555555555,
    "skillsImprovement": -0.02000000000000013,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8633333333333333,
    "updatedAt": "2026-09-03T17:11:48.710Z",
    "tokens": {
      "promptTokens": 352,
      "completionTokens": 10612,
      "totalTokens": 10964
    },
    "costUsd": 0.106824,
    "durationMs": 81840,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8800000000000001,
    "improvement": 0.01666666666666683,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8800000000000001,
    "skillsImprovement": 0.01666666666666683,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8311688311688311,
    "updatedAt": "2026-09-03T17:10:20.435Z",
    "tokens": {
      "promptTokens": 369,
      "completionTokens": 369,
      "totalTokens": 738
    },
    "costUsd": 0.004428,
    "durationMs": 10861,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8311688311688311,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8311688311688311,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8221997300944669,
    "updatedAt": "2026-09-03T17:09:34.496Z",
    "tokens": {
      "promptTokens": 303,
      "completionTokens": 1965,
      "totalTokens": 2268
    },
    "costUsd": 0.020256,
    "durationMs": 30375,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8478407557354926,
    "improvement": 0.02564102564102566,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": 0.05128205128205132,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7113636363636364,
    "updatedAt": "2026-09-03T17:10:26.728Z",
    "tokens": {
      "promptTokens": 168,
      "completionTokens": 2599,
      "totalTokens": 2767
    },
    "costUsd": 0.026326,
    "durationMs": 33308,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8090909090909091,
    "improvement": 0.09772727272727266,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7818181818181819,
    "skillsImprovement": 0.07045454545454544,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:10:11.192Z",
    "tokens": {
      "promptTokens": 422,
      "completionTokens": 2147,
      "totalTokens": 2569
    },
    "costUsd": 0.022314,
    "durationMs": 23197,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7363636363636363,
    "updatedAt": "2026-09-03T17:10:35.770Z",
    "tokens": {
      "promptTokens": 327,
      "completionTokens": 1054,
      "totalTokens": 1381
    },
    "costUsd": 0.011194,
    "durationMs": 11298,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7085858585858587,
    "improvement": -0.02777777777777768,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.7116161616161616,
    "skillsImprovement": -0.02474747474747474,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:11:52.470Z",
    "tokens": {
      "promptTokens": 1967,
      "completionTokens": 2232,
      "totalTokens": 4199
    },
    "costUsd": 0.026254,
    "durationMs": 25346,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": 0.30000000000000004,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-03T17:09:37.301Z",
    "tokens": {
      "promptTokens": 2142,
      "completionTokens": 1043,
      "totalTokens": 3185
    },
    "costUsd": 0.014714,
    "durationMs": 11465,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.7647058823529411,
    "improvement": -0.05882352941176472,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T17:12:46.192Z",
    "tokens": {
      "promptTokens": 1737,
      "completionTokens": 5569,
      "totalTokens": 7306
    },
    "costUsd": 0.059164,
    "durationMs": 57244,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.5,
    "improvement": 0.16666666666666669,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333333,
    "updatedAt": "2026-09-03T17:12:30.987Z",
    "tokens": {
      "promptTokens": 182,
      "completionTokens": 12731,
      "totalTokens": 12913
    },
    "costUsd": 0.127674,
    "durationMs": 99523,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": 0.08333333333333348,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.3333333333333335,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-sonnet-5",
    "label": "Claude Sonnet 5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:11:47.035Z",
    "tokens": {
      "promptTokens": 92,
      "completionTokens": 7086,
      "totalTokens": 7178
    },
    "costUsd": 0.071044,
    "durationMs": 55481,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-28T20:23:04.695Z",
    "tokens": {
      "promptTokens": 1421,
      "completionTokens": 8932,
      "totalTokens": 10353
    },
    "costUsd": 0.011144699999999999,
    "durationMs": 57591,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.7142857142857143,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.2857142857142857,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.8444444444444444,
    "updatedAt": "2026-09-28T20:23:03.054Z",
    "tokens": {
      "promptTokens": 141,
      "completionTokens": 20072,
      "totalTokens": 20213
    },
    "costUsd": 0.024128699999999996,
    "durationMs": 84486,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.8944444444444444,
    "improvement": 0.04999999999999993,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.55,
    "skillsImprovement": -0.2944444444444444,
    "skillsCoverage": "2/2"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:22:37.975Z",
    "tokens": {
      "promptTokens": 84,
      "completionTokens": 12630,
      "totalTokens": 12714
    },
    "costUsd": 0.0151812,
    "durationMs": 49848,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 0.8,
    "improvement": -0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": -0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:22:25.596Z",
    "tokens": {
      "promptTokens": 1239,
      "completionTokens": 4018,
      "totalTokens": 5257
    },
    "costUsd": 0.0051933,
    "durationMs": 30107,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": -0.09090909090909094,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:20:00.843Z",
    "tokens": {
      "promptTokens": 268,
      "completionTokens": 1704,
      "totalTokens": 1972
    },
    "costUsd": 0.0021252,
    "durationMs": 11326,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9527777777777778,
    "updatedAt": "2026-09-28T20:19:48.397Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 1675,
      "totalTokens": 1891
    },
    "costUsd": 0.0020748000000000003,
    "durationMs": 6350,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9777777777777779,
    "improvement": 0.025000000000000022,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.78,
    "skillsImprovement": -0.1727777777777778,
    "skillsCoverage": "5/5"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-28T20:22:06.721Z",
    "tokens": {
      "promptTokens": 246,
      "completionTokens": 15671,
      "totalTokens": 15917
    },
    "costUsd": 0.018879,
    "durationMs": 54597,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9523809523809524,
    "updatedAt": "2026-09-28T20:20:40.586Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 922,
      "totalTokens": 1177
    },
    "costUsd": 0.0011829,
    "durationMs": 10343,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9523809523809524,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9220779220779222,
    "skillsImprovement": -0.030303030303030276,
    "skillsCoverage": "3/3"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8734817813765182,
    "updatedAt": "2026-09-28T20:20:29.971Z",
    "tokens": {
      "promptTokens": 235,
      "completionTokens": 7355,
      "totalTokens": 7590
    },
    "costUsd": 0.0088965,
    "durationMs": 47904,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8478407557354926,
    "improvement": -0.02564102564102566,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8756185335132703,
    "skillsImprovement": 0.002136752136752129,
    "skillsCoverage": "3/3"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7840909090909092,
    "updatedAt": "2026-09-28T20:21:29.454Z",
    "tokens": {
      "promptTokens": 135,
      "completionTokens": 12223,
      "totalTokens": 12358
    },
    "costUsd": 0.0147081,
    "durationMs": 70631,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8772727272727272,
    "improvement": 0.09318181818181803,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8272727272727272,
    "skillsImprovement": 0.04318181818181799,
    "skillsCoverage": "4/4"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-28T20:20:32.588Z",
    "tokens": {
      "promptTokens": 295,
      "completionTokens": 4321,
      "totalTokens": 4616
    },
    "costUsd": 0.0052737,
    "durationMs": 31355,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8141414141414142,
    "updatedAt": "2026-09-28T20:21:25.318Z",
    "tokens": {
      "promptTokens": 239,
      "completionTokens": 7932,
      "totalTokens": 8171
    },
    "costUsd": 0.0095901,
    "durationMs": 40735,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7616161616161617,
    "improvement": -0.05252525252525242,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8227272727272728,
    "skillsImprovement": 0.008585858585858586,
    "skillsCoverage": "3/3"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:22:15.978Z",
    "tokens": {
      "promptTokens": 1358,
      "completionTokens": 2714,
      "totalTokens": 4072
    },
    "costUsd": 0.0036642,
    "durationMs": 13194,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-28T20:20:30.108Z",
    "tokens": {
      "promptTokens": 1338,
      "completionTokens": 5215,
      "totalTokens": 6553
    },
    "costUsd": 0.006659399999999999,
    "durationMs": 48040,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8823529411764706,
    "improvement": -0.11764705882352944,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": -0.17647058823529416,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:22:56.308Z",
    "tokens": {
      "promptTokens": 1170,
      "completionTokens": 7643,
      "totalTokens": 8813
    },
    "costUsd": 0.0095226,
    "durationMs": 39937,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.5,
    "improvement": -0.5,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.6666666666666667,
    "updatedAt": "2026-09-28T20:22:40.519Z",
    "tokens": {
      "promptTokens": 133,
      "completionTokens": 19292,
      "totalTokens": 19425
    },
    "costUsd": 0.0231903,
    "durationMs": 70666,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": 0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.5833333333333334,
    "skillsImprovement": -0.08333333333333337,
    "skillsCoverage": "2/2"
  },
  {
    "model": "deepseek-v4.1-flash",
    "label": "DeepSeek V4.1 Flash",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:23:05.862Z",
    "tokens": {
      "promptTokens": 82,
      "completionTokens": 22560,
      "totalTokens": 22642
    },
    "costUsd": 0.0270966,
    "durationMs": 90781,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "deepseek",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.5714285714285714,
    "updatedAt": "2026-09-03T17:24:15.652Z",
    "tokens": {
      "promptTokens": 1536,
      "completionTokens": 7158,
      "totalTokens": 8694
    },
    "costUsd": 0.088968,
    "durationMs": 56831,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.2857142857142857,
    "improvement": -0.2857142857142857,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5714285714285714,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.4222222222222222,
    "updatedAt": "2026-09-03T17:24:15.298Z",
    "tokens": {
      "promptTokens": 117,
      "completionTokens": 8723,
      "totalTokens": 8840
    },
    "costUsd": 0.10491,
    "durationMs": 67393,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.4222222222222222,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.4222222222222222,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:23:46.460Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 4600,
      "totalTokens": 4659
    },
    "costUsd": 0.055318,
    "durationMs": 35263,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.8181818181818182,
    "updatedAt": "2026-09-03T17:23:40.169Z",
    "tokens": {
      "promptTokens": 1330,
      "completionTokens": 2983,
      "totalTokens": 4313
    },
    "costUsd": 0.038456,
    "durationMs": 28874,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.7272727272727273,
    "improvement": -0.09090909090909094,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7272727272727273,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:22:25.239Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 3877,
      "totalTokens": 4132
    },
    "costUsd": 0.047034,
    "durationMs": 28185,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9105555555555556,
    "updatedAt": "2026-09-03T17:22:28.422Z",
    "tokens": {
      "promptTokens": 197,
      "completionTokens": 5744,
      "totalTokens": 5941
    },
    "costUsd": 0.069322,
    "durationMs": 41141,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9550000000000001,
    "improvement": 0.04444444444444451,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9327777777777777,
    "skillsImprovement": 0.022222222222222143,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8800000000000001,
    "updatedAt": "2026-09-03T17:23:12.482Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 6329,
      "totalTokens": 6545
    },
    "costUsd": 0.07638,
    "durationMs": 43896,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8466666666666667,
    "improvement": -0.03333333333333344,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8466666666666667,
    "skillsImprovement": -0.03333333333333344,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9090909090909092,
    "updatedAt": "2026-09-03T17:22:54.770Z",
    "tokens": {
      "promptTokens": 237,
      "completionTokens": 4799,
      "totalTokens": 5036
    },
    "costUsd": 0.058062,
    "durationMs": 39061,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.7835497835497836,
    "improvement": -0.12554112554112562,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9047619047619048,
    "skillsImprovement": -0.0043290043290044045,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8734817813765182,
    "updatedAt": "2026-09-03T17:22:04.873Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 1891,
      "totalTokens": 2103
    },
    "costUsd": 0.023116,
    "durationMs": 22195,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.6613636363636364,
    "updatedAt": "2026-09-03T17:22:41.781Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 1857,
      "totalTokens": 1967
    },
    "costUsd": 0.022504,
    "durationMs": 31205,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.6840909090909091,
    "improvement": 0.022727272727272707,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.6136363636363636,
    "skillsImprovement": -0.04772727272727273,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:22:23.097Z",
    "tokens": {
      "promptTokens": 284,
      "completionTokens": 2886,
      "totalTokens": 3170
    },
    "costUsd": 0.0352,
    "durationMs": 24949,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.6116161616161616,
    "updatedAt": "2026-09-03T17:22:57.084Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 4657,
      "totalTokens": 4882
    },
    "costUsd": 0.056334,
    "durationMs": 32996,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.694949494949495,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8257575757575758,
    "skillsImprovement": 0.2141414141414142,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:23:42.866Z",
    "tokens": {
      "promptTokens": 1457,
      "completionTokens": 3682,
      "totalTokens": 5139
    },
    "costUsd": 0.047098,
    "durationMs": 30240,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.5,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:21:58.003Z",
    "tokens": {
      "promptTokens": 1376,
      "completionTokens": 1682,
      "totalTokens": 3058
    },
    "costUsd": 0.022936,
    "durationMs": 14057,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T17:24:17.794Z",
    "tokens": {
      "promptTokens": 1242,
      "completionTokens": 5838,
      "totalTokens": 7080
    },
    "costUsd": 0.07254,
    "durationMs": 44191,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6666666666666667,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.41666666666666663,
    "updatedAt": "2026-09-03T17:23:51.176Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 7136,
      "totalTokens": 7246
    },
    "costUsd": 0.085852,
    "durationMs": 52088,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5833333333333334,
    "improvement": 0.16666666666666674,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.5000000000000001,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.1-pro-preview",
    "label": "Gemini 3.1 Pro Preview",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:23:42.967Z",
    "tokens": {
      "promptTokens": 57,
      "completionTokens": 5344,
      "totalTokens": 5401
    },
    "costUsd": 0.064242,
    "durationMs": 41853,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.5714285714285714,
    "updatedAt": "2026-09-03T17:21:44.882Z",
    "tokens": {
      "promptTokens": 1536,
      "completionTokens": 927,
      "totalTokens": 2463
    },
    "costUsd": 0.0027783,
    "durationMs": 7066,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.5714285714285714,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5714285714285714,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.5777777777777777,
    "updatedAt": "2026-09-03T17:21:51.122Z",
    "tokens": {
      "promptTokens": 117,
      "completionTokens": 4395,
      "totalTokens": 4512
    },
    "costUsd": 0.0110226,
    "durationMs": 17665,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.5222222222222221,
    "improvement": -0.05555555555555558,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.5722222222222222,
    "skillsImprovement": -0.005555555555555536,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:21:48.087Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 3048,
      "totalTokens": 3107
    },
    "costUsd": 0.0076377,
    "durationMs": 13266,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.8181818181818182,
    "updatedAt": "2026-09-03T17:21:47.109Z",
    "tokens": {
      "promptTokens": 1330,
      "completionTokens": 577,
      "totalTokens": 1907
    },
    "costUsd": 0.0018415,
    "durationMs": 11731,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0.18181818181818177,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": 0.09090909090909083,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:21:07.861Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 192,
      "totalTokens": 447
    },
    "costUsd": 0.0005565,
    "durationMs": 1292,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9327777777777777,
    "updatedAt": "2026-09-03T17:21:02.548Z",
    "tokens": {
      "promptTokens": 197,
      "completionTokens": 411,
      "totalTokens": 608
    },
    "costUsd": 0.0010865999999999998,
    "durationMs": 1970,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9577777777777777,
    "improvement": 0.025000000000000022,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9105555555555556,
    "skillsImprovement": -0.022222222222222143,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8666666666666668,
    "updatedAt": "2026-09-03T17:21:38.108Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 3389,
      "totalTokens": 3605
    },
    "costUsd": 0.0085373,
    "durationMs": 11881,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8,
    "improvement": -0.06666666666666676,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8666666666666666,
    "skillsImprovement": -2.220446049250313e-16,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.7056277056277057,
    "updatedAt": "2026-09-03T17:21:26.097Z",
    "tokens": {
      "promptTokens": 237,
      "completionTokens": 570,
      "totalTokens": 807
    },
    "costUsd": 0.0014961,
    "durationMs": 9834,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8008658008658008,
    "improvement": 0.09523809523809512,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8484848484848485,
    "skillsImprovement": 0.1428571428571428,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.599527665317139,
    "updatedAt": "2026-09-03T17:21:06.549Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 999,
      "totalTokens": 1211
    },
    "costUsd": 0.0025610999999999997,
    "durationMs": 11926,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.6939946018893387,
    "improvement": 0.09446693657219973,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": 0.27395411605937925,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.6886363636363636,
    "updatedAt": "2026-09-03T17:21:27.855Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 2333,
      "totalTokens": 2443
    },
    "costUsd": 0.0058655,
    "durationMs": 16451,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7840909090909092,
    "improvement": 0.09545454545454557,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8522727272727273,
    "skillsImprovement": 0.1636363636363637,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-03T17:21:17.604Z",
    "tokens": {
      "promptTokens": 284,
      "completionTokens": 1325,
      "totalTokens": 1609
    },
    "costUsd": 0.0033977,
    "durationMs": 10922,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.6616161616161617,
    "updatedAt": "2026-09-03T17:21:23.166Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 530,
      "totalTokens": 755
    },
    "costUsd": 0.0013925,
    "durationMs": 2138,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.5202020202020202,
    "improvement": -0.14141414141414144,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.5176767676767677,
    "skillsImprovement": -0.14393939393939392,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:21:41.043Z",
    "tokens": {
      "promptTokens": 1457,
      "completionTokens": 597,
      "totalTokens": 2054
    },
    "costUsd": 0.0019295999999999998,
    "durationMs": 3834,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.5,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:20:59.247Z",
    "tokens": {
      "promptTokens": 1376,
      "completionTokens": 508,
      "totalTokens": 1884
    },
    "costUsd": 0.0016828,
    "durationMs": 4266,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T17:21:43.793Z",
    "tokens": {
      "promptTokens": 1242,
      "completionTokens": 812,
      "totalTokens": 2054
    },
    "costUsd": 0.0024026,
    "durationMs": 5539,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6666666666666667,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333333,
    "updatedAt": "2026-09-03T17:21:42.012Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 3143,
      "totalTokens": 3253
    },
    "costUsd": 0.0078905,
    "durationMs": 12015,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.41666666666666663,
    "improvement": -0.16666666666666663,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.3333333333333335,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.5-flash-lite",
    "label": "Gemini 3.5 Flash-Lite",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:21:43.860Z",
    "tokens": {
      "promptTokens": 57,
      "completionTokens": 3081,
      "totalTokens": 3138
    },
    "costUsd": 0.0077196,
    "durationMs": 13529,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-03T17:21:09.337Z",
    "tokens": {
      "promptTokens": 1536,
      "completionTokens": 5253,
      "totalTokens": 6789
    },
    "costUsd": 0.02085075,
    "durationMs": 28126,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.42857142857142855,
    "improvement": -0.28571428571428575,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.42857142857142855,
    "skillsImprovement": -0.28571428571428575,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.5722222222222222,
    "updatedAt": "2026-09-03T17:21:18.121Z",
    "tokens": {
      "promptTokens": 117,
      "completionTokens": 12255,
      "totalTokens": 12372
    },
    "costUsd": 0.046044,
    "durationMs": 68229,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.7333333333333334,
    "improvement": 0.1611111111111112,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.5722222222222222,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Android",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:20:54.107Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 8133,
      "totalTokens": 8192
    },
    "costUsd": 0.030543,
    "durationMs": 40962,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.8181818181818182,
    "updatedAt": "2026-09-03T17:20:54.492Z",
    "tokens": {
      "promptTokens": 1330,
      "completionTokens": 2969,
      "totalTokens": 4299
    },
    "costUsd": 0.01213125,
    "durationMs": 26763,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0.18181818181818177,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.18181818181818177,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:18:57.656Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 1670,
      "totalTokens": 1925
    },
    "costUsd": 0.00645375,
    "durationMs": 7330,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9555555555555555,
    "updatedAt": "2026-09-03T17:18:53.778Z",
    "tokens": {
      "promptTokens": 197,
      "completionTokens": 2329,
      "totalTokens": 2526
    },
    "costUsd": 0.0088815,
    "durationMs": 10294,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.7355555555555555,
    "improvement": -0.21999999999999997,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9555555555555555,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8833333333333334,
    "updatedAt": "2026-09-03T17:20:45.155Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 13756,
      "totalTokens": 13972
    },
    "costUsd": 0.051747,
    "durationMs": 61312,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0.033333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8966666666666667,
    "skillsImprovement": 0.013333333333333308,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8268398268398268,
    "updatedAt": "2026-09-03T17:19:40.899Z",
    "tokens": {
      "promptTokens": 237,
      "completionTokens": 3744,
      "totalTokens": 3981
    },
    "costUsd": 0.01421775,
    "durationMs": 28499,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8917748917748919,
    "improvement": 0.06493506493506507,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.6060606060606061,
    "skillsImprovement": -0.22077922077922074,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8910256410256411,
    "updatedAt": "2026-09-03T17:18:54.768Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 2848,
      "totalTokens": 3060
    },
    "costUsd": 0.010839,
    "durationMs": 23472,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": -0.01754385964912286,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": -0.01754385964912286,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8522727272727273,
    "updatedAt": "2026-09-03T17:20:07.839Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 12821,
      "totalTokens": 12931
    },
    "costUsd": 0.04816125,
    "durationMs": 66747,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8318181818181818,
    "improvement": -0.020454545454545503,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8295454545454546,
    "skillsImprovement": -0.022727272727272707,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:19:15.080Z",
    "tokens": {
      "promptTokens": 284,
      "completionTokens": 3374,
      "totalTokens": 3658
    },
    "costUsd": 0.0128655,
    "durationMs": 20834,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.753030303030303,
    "updatedAt": "2026-09-03T17:19:47.431Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 4120,
      "totalTokens": 4345
    },
    "costUsd": 0.01561875,
    "durationMs": 18700,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8196969696969697,
    "improvement": 0.06666666666666665,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8863636363636364,
    "skillsImprovement": 0.1333333333333333,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:20:49.918Z",
    "tokens": {
      "promptTokens": 1457,
      "completionTokens": 3281,
      "totalTokens": 4738
    },
    "costUsd": 0.0133965,
    "durationMs": 17706,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": 0.30000000000000004,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:18:41.529Z",
    "tokens": {
      "promptTokens": 1376,
      "completionTokens": 1477,
      "totalTokens": 2853
    },
    "costUsd": 0.00657075,
    "durationMs": 8844,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8235294117647058,
    "improvement": -0.17647058823529416,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": -0.17647058823529416,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.16666666666666666,
    "updatedAt": "2026-09-03T17:21:16.129Z",
    "tokens": {
      "promptTokens": 1242,
      "completionTokens": 5259,
      "totalTokens": 6501
    },
    "costUsd": 0.02065275,
    "durationMs": 30816,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0.16666666666666666,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.8333333333333334,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.41666666666666663,
    "updatedAt": "2026-09-03T17:20:54.835Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 9244,
      "totalTokens": 9354
    },
    "costUsd": 0.0347475,
    "durationMs": 50846,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.5000000000000001,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.6-flash",
    "label": "Gemini 3.6 Flash",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:21:00.394Z",
    "tokens": {
      "promptTokens": 57,
      "completionTokens": 11491,
      "totalTokens": 11548
    },
    "costUsd": 0.043134,
    "durationMs": 54204,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-03T17:18:49.400Z",
    "tokens": {
      "promptTokens": 1536,
      "completionTokens": 2885,
      "totalTokens": 4421
    },
    "costUsd": 0.01197075,
    "durationMs": 28863,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.42857142857142855,
    "improvement": -0.28571428571428575,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.42857142857142855,
    "skillsImprovement": -0.28571428571428575,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.6277777777777778,
    "updatedAt": "2026-09-03T17:19:32.939Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 10881,
      "totalTokens": 11000
    },
    "costUsd": 0.040893,
    "durationMs": 90481,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.6277777777777778,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7944444444444444,
    "skillsImprovement": 0.16666666666666663,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:18:43.011Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 6041,
      "totalTokens": 6100
    },
    "costUsd": 0.022698,
    "durationMs": 36103,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:18:53.401Z",
    "tokens": {
      "promptTokens": 1330,
      "completionTokens": 1951,
      "totalTokens": 3281
    },
    "costUsd": 0.00831375,
    "durationMs": 44834,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:16:48.331Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 1043,
      "totalTokens": 1298
    },
    "costUsd": 0.0041025,
    "durationMs": 7086,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9577777777777777,
    "updatedAt": "2026-09-03T17:17:46.442Z",
    "tokens": {
      "promptTokens": 199,
      "completionTokens": 1651,
      "totalTokens": 1850
    },
    "costUsd": 0.0063405,
    "durationMs": 74126,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9577777777777777,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9555555555555555,
    "skillsImprovement": -0.0022222222222222365,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8833333333333334,
    "updatedAt": "2026-09-03T17:18:20.408Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 7121,
      "totalTokens": 7337
    },
    "costUsd": 0.02686575,
    "durationMs": 38995,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8833333333333334,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9,
    "skillsImprovement": 0.016666666666666607,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8138528138528138,
    "updatedAt": "2026-09-03T17:17:25.640Z",
    "tokens": {
      "promptTokens": 237,
      "completionTokens": 1220,
      "totalTokens": 1457
    },
    "costUsd": 0.00475275,
    "durationMs": 15799,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9220779220779222,
    "improvement": 0.10822510822510834,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8614718614718614,
    "skillsImprovement": 0.04761904761904756,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8734817813765182,
    "updatedAt": "2026-09-03T17:16:40.220Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 1498,
      "totalTokens": 1710
    },
    "costUsd": 0.0057765,
    "durationMs": 17044,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7363636363636363,
    "updatedAt": "2026-09-03T17:17:36.732Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 3735,
      "totalTokens": 3845
    },
    "costUsd": 0.01408875,
    "durationMs": 32901,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7863636363636364,
    "improvement": 0.050000000000000044,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7840909090909092,
    "skillsImprovement": 0.04772727272727284,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.8333333333333334,
    "updatedAt": "2026-09-03T17:17:09.089Z",
    "tokens": {
      "promptTokens": 284,
      "completionTokens": 2307,
      "totalTokens": 2591
    },
    "costUsd": 0.00886425,
    "durationMs": 20632,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.16666666666666663,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.16666666666666663,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8474747474747475,
    "updatedAt": "2026-09-03T17:17:41.289Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 1540,
      "totalTokens": 1765
    },
    "costUsd": 0.00594375,
    "durationMs": 11279,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8196969696969697,
    "improvement": -0.02777777777777779,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9141414141414143,
    "skillsImprovement": 0.06666666666666676,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:18:31.170Z",
    "tokens": {
      "promptTokens": 1457,
      "completionTokens": 2501,
      "totalTokens": 3958
    },
    "costUsd": 0.0104715,
    "durationMs": 16985,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:16:33.210Z",
    "tokens": {
      "promptTokens": 1376,
      "completionTokens": 565,
      "totalTokens": 1941
    },
    "costUsd": 0.00315075,
    "durationMs": 7162,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T17:18:40.628Z",
    "tokens": {
      "promptTokens": 1242,
      "completionTokens": 1886,
      "totalTokens": 3128
    },
    "costUsd": 0.008004,
    "durationMs": 13863,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333333,
    "updatedAt": "2026-09-03T17:18:29.403Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 5630,
      "totalTokens": 5740
    },
    "costUsd": 0.021195,
    "durationMs": 31438,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": 0.08333333333333348,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.3333333333333335,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.7-flash",
    "label": "Gemini 3.7 Flash",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:18:26.555Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 6920,
      "totalTokens": 6979
    },
    "costUsd": 0.02599425,
    "durationMs": 24576,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.5714285714285714,
    "updatedAt": "2026-09-03T17:17:26.944Z",
    "tokens": {
      "promptTokens": 1536,
      "completionTokens": 7509,
      "totalTokens": 9045
    },
    "costUsd": 0.02931075,
    "durationMs": 77476,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.42857142857142855,
    "improvement": -0.14285714285714285,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5714285714285714,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.6277777777777778,
    "updatedAt": "2026-09-03T17:16:09.325Z",
    "tokens": {
      "promptTokens": 117,
      "completionTokens": 8701,
      "totalTokens": 8818
    },
    "costUsd": 0.0327165,
    "durationMs": 50608,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.6833333333333333,
    "improvement": 0.05555555555555558,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7388888888888889,
    "skillsImprovement": 0.11111111111111116,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:16:14.738Z",
    "tokens": {
      "promptTokens": 59,
      "completionTokens": 6604,
      "totalTokens": 6663
    },
    "costUsd": 0.02480925,
    "durationMs": 39688,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:16:32.037Z",
    "tokens": {
      "promptTokens": 1330,
      "completionTokens": 3230,
      "totalTokens": 4560
    },
    "costUsd": 0.01311,
    "durationMs": 40443,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:12:53.428Z",
    "tokens": {
      "promptTokens": 255,
      "completionTokens": 1505,
      "totalTokens": 1760
    },
    "costUsd": 0.005835,
    "durationMs": 9918,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9555555555555555,
    "updatedAt": "2026-09-03T17:12:43.827Z",
    "tokens": {
      "promptTokens": 197,
      "completionTokens": 2381,
      "totalTokens": 2578
    },
    "costUsd": 0.0090765,
    "durationMs": 14904,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9555555555555555,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9777777777777779,
    "skillsImprovement": 0.022222222222222365,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8833333333333334,
    "updatedAt": "2026-09-03T17:14:55.883Z",
    "tokens": {
      "promptTokens": 216,
      "completionTokens": 7352,
      "totalTokens": 7568
    },
    "costUsd": 0.027732,
    "durationMs": 64513,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8833333333333334,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8833333333333334,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779222,
    "updatedAt": "2026-09-03T17:15:18.592Z",
    "tokens": {
      "promptTokens": 237,
      "completionTokens": 14489,
      "totalTokens": 14726
    },
    "costUsd": 0.0545115,
    "durationMs": 136598,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9220779220779222,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9523809523809524,
    "skillsImprovement": 0.030303030303030276,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8910256410256411,
    "updatedAt": "2026-09-03T17:12:35.209Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 1933,
      "totalTokens": 2145
    },
    "costUsd": 0.00740775,
    "durationMs": 38516,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": -0.01754385964912286,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8734817813765182,
    "skillsImprovement": -0.01754385964912286,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7136363636363636,
    "updatedAt": "2026-09-03T17:13:47.583Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 3240,
      "totalTokens": 3350
    },
    "costUsd": 0.0122325,
    "durationMs": 54016,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7840909090909092,
    "improvement": 0.07045454545454555,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7613636363636365,
    "skillsImprovement": 0.04772727272727284,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-03T17:13:21.638Z",
    "tokens": {
      "promptTokens": 284,
      "completionTokens": 2258,
      "totalTokens": 2542
    },
    "costUsd": 0.0086805,
    "durationMs": 37513,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8141414141414142,
    "updatedAt": "2026-09-03T17:14:54.914Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 9915,
      "totalTokens": 10140
    },
    "costUsd": 0.03735,
    "durationMs": 93135,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8474747474747475,
    "improvement": 0.033333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8474747474747475,
    "skillsImprovement": 0.033333333333333326,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:16:23.040Z",
    "tokens": {
      "promptTokens": 1457,
      "completionTokens": 3913,
      "totalTokens": 5370
    },
    "costUsd": 0.0157665,
    "durationMs": 28659,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:12:24.693Z",
    "tokens": {
      "promptTokens": 1376,
      "completionTokens": 942,
      "totalTokens": 2318
    },
    "costUsd": 0.0045645,
    "durationMs": 11027,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8823529411764706,
    "skillsImprovement": -0.11764705882352944,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T17:18:02.185Z",
    "tokens": {
      "promptTokens": 1244,
      "completionTokens": 16364,
      "totalTokens": 17608
    },
    "costUsd": 0.062298,
    "durationMs": 112231,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5,
    "updatedAt": "2026-09-03T17:16:25.917Z",
    "tokens": {
      "promptTokens": 110,
      "completionTokens": 5121,
      "totalTokens": 5231
    },
    "costUsd": 0.01928625,
    "durationMs": 74582,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5833333333333333,
    "improvement": 0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.5,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gemini-3.8-flash",
    "label": "Gemini 3.8 Flash",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:15:51.454Z",
    "tokens": {
      "promptTokens": 57,
      "completionTokens": 6881,
      "totalTokens": 6938
    },
    "costUsd": 0.0258465,
    "durationMs": 38292,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "google",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-28T20:27:32.832Z",
    "tokens": {
      "promptTokens": 1355,
      "completionTokens": 3217,
      "totalTokens": 4572
    },
    "costUsd": 0.00181175,
    "durationMs": 22674,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.1428571428571429,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.6277777777777778,
    "updatedAt": "2026-09-28T20:28:52.802Z",
    "tokens": {
      "promptTokens": 125,
      "completionTokens": 32768,
      "totalTokens": 32893
    },
    "costUsd": 0.01640275,
    "durationMs": 273081,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.4722222222222222,
    "improvement": -0.15555555555555556,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": 0.3222222222222222,
    "skillsCoverage": "2/2"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:28:37.630Z",
    "tokens": {
      "promptTokens": 68,
      "completionTokens": 20824,
      "totalTokens": 20892
    },
    "costUsd": 0.010422200000000001,
    "durationMs": 155461,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": -0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.7272727272727273,
    "updatedAt": "2026-09-28T20:26:58.540Z",
    "tokens": {
      "promptTokens": 1203,
      "completionTokens": 1556,
      "totalTokens": 2759
    },
    "costUsd": 0.00095845,
    "durationMs": 16382,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": 0.18181818181818177,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.2727272727272727,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:23:31.568Z",
    "tokens": {
      "promptTokens": 248,
      "completionTokens": 3191,
      "totalTokens": 3439
    },
    "costUsd": 0.0016327,
    "durationMs": 28135,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9,
    "skillsImprovement": -0.09999999999999998,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9155555555555555,
    "updatedAt": "2026-09-28T20:23:02.778Z",
    "tokens": {
      "promptTokens": 192,
      "completionTokens": 755,
      "totalTokens": 947
    },
    "costUsd": 0.0004063,
    "durationMs": 6078,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9527777777777778,
    "improvement": 0.03722222222222238,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9777777777777779,
    "skillsImprovement": 0.0622222222222224,
    "skillsCoverage": "5/5"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8633333333333333,
    "updatedAt": "2026-09-28T21:01:40.484Z",
    "tokens": {
      "promptTokens": 221,
      "completionTokens": 3562,
      "totalTokens": 3783
    },
    "costUsd": 0.00181415,
    "durationMs": 13623,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8966666666666667,
    "improvement": 0.03333333333333344,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.7166666666666667,
    "skillsImprovement": -0.1466666666666666,
    "skillsCoverage": "5/5"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-28T20:23:28.488Z",
    "tokens": {
      "promptTokens": 228,
      "completionTokens": 464,
      "totalTokens": 692
    },
    "costUsd": 0.00026619999999999997,
    "durationMs": 7532,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8198051948051948,
    "improvement": -0.04166666666666663,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9220779220779222,
    "skillsImprovement": 0.060606060606060774,
    "skillsCoverage": "3/3"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8200629779577148,
    "updatedAt": "2026-09-28T20:23:22.461Z",
    "tokens": {
      "promptTokens": 219,
      "completionTokens": 4363,
      "totalTokens": 4582
    },
    "costUsd": 0.00221435,
    "durationMs": 42563,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8478407557354926,
    "improvement": 0.02777777777777779,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8756185335132703,
    "skillsImprovement": 0.05555555555555558,
    "skillsCoverage": "3/3"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.6886363636363637,
    "updatedAt": "2026-09-28T20:23:32.420Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 2395,
      "totalTokens": 2514
    },
    "costUsd": 0.0012153499999999998,
    "durationMs": 21859,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7113636363636364,
    "improvement": 0.022727272727272707,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.5977272727272727,
    "skillsImprovement": -0.09090909090909105,
    "skillsCoverage": "4/4"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-28T20:23:20.547Z",
    "tokens": {
      "promptTokens": 272,
      "completionTokens": 1810,
      "totalTokens": 2082
    },
    "costUsd": 0.0009458,
    "durationMs": 16537,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.6838383838383839,
    "updatedAt": "2026-09-28T20:23:27.753Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 533,
      "totalTokens": 750
    },
    "costUsd": 0.00029905000000000003,
    "durationMs": 2870,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8141414141414142,
    "improvement": 0.13030303030303025,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8505050505050505,
    "skillsImprovement": 0.16666666666666663,
    "skillsCoverage": "3/3"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:28:02.436Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 7590,
      "totalTokens": 8910
    },
    "costUsd": 0.003993,
    "durationMs": 63478,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": -0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-28T20:22:44.946Z",
    "tokens": {
      "promptTokens": 1275,
      "completionTokens": 550,
      "totalTokens": 1825
    },
    "costUsd": 0.00046625,
    "durationMs": 4044,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.9411764705882353,
    "improvement": -0.05882352941176472,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": -0.17647058823529416,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-28T20:27:53.893Z",
    "tokens": {
      "promptTokens": 1133,
      "completionTokens": 3149,
      "totalTokens": 4282
    },
    "costUsd": 0.00174445,
    "durationMs": 20659,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6666666666666667,
    "skillsCoverage": "1/1"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.75,
    "updatedAt": "2026-09-28T21:02:10.118Z",
    "tokens": {
      "promptTokens": 118,
      "completionTokens": 5241,
      "totalTokens": 5359
    },
    "costUsd": 0.0026382,
    "durationMs": 21296,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": -0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.16666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "glm-5.3-flash",
    "label": "GLM 5.3 Flash",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:32:26.686Z",
    "tokens": {
      "promptTokens": 66,
      "completionTokens": 17680,
      "totalTokens": 17746
    },
    "costUsd": 0.008849899999999999,
    "durationMs": 517724,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "zai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.5714285714285714,
    "updatedAt": "2026-09-03T16:59:16.542Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 3720,
      "totalTokens": 5084
    },
    "costUsd": 0.0047368,
    "durationMs": 46594,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.5714285714285714,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.42857142857142855,
    "skillsImprovement": -0.14285714285714285,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.5722222222222222,
    "updatedAt": "2026-09-03T16:59:13.699Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 5461,
      "totalTokens": 5580
    },
    "costUsd": 0.006577,
    "durationMs": 56604,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.5777777777777777,
    "improvement": 0.005555555555555536,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7388888888888889,
    "skillsImprovement": 0.16666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:59:03.450Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 3754,
      "totalTokens": 3819
    },
    "costUsd": 0.0045178,
    "durationMs": 43720,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:58:51.675Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 1593,
      "totalTokens": 2795
    },
    "costUsd": 0.002152,
    "durationMs": 28132,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:57:29.493Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 236,
      "totalTokens": 480
    },
    "costUsd": 0.000332,
    "durationMs": 3361,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.8705555555555555,
    "updatedAt": "2026-09-03T16:57:26.981Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 798,
      "totalTokens": 989
    },
    "costUsd": 0.0009958,
    "durationMs": 8276,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.8955555555555555,
    "improvement": 0.025000000000000022,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9577777777777777,
    "skillsImprovement": 0.0872222222222222,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9333333333333332,
    "updatedAt": "2026-09-03T16:58:29.811Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 2981,
      "totalTokens": 3198
    },
    "costUsd": 0.0036206,
    "durationMs": 28437,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9333333333333332,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333332,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8917748917748919,
    "updatedAt": "2026-09-03T16:58:04.599Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 1301,
      "totalTokens": 1525
    },
    "costUsd": 0.001606,
    "durationMs": 19857,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8917748917748919,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8917748917748919,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8580746738641475,
    "updatedAt": "2026-09-03T16:57:40.973Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 1800,
      "totalTokens": 2014
    },
    "costUsd": 0.0022028,
    "durationMs": 34331,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8302968960863698,
    "improvement": -0.02777777777777768,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8302968960863698,
    "skillsImprovement": -0.02777777777777768,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7113636363636364,
    "updatedAt": "2026-09-03T16:58:14.862Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 2577,
      "totalTokens": 2690
    },
    "costUsd": 0.003115,
    "durationMs": 41397,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7340909090909091,
    "improvement": 0.022727272727272707,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7568181818181818,
    "skillsImprovement": 0.045454545454545414,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-03T16:57:46.981Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1376,
      "totalTokens": 1646
    },
    "costUsd": 0.0017052,
    "durationMs": 19792,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.9085858585858585,
    "updatedAt": "2026-09-03T16:58:00.729Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 688,
      "totalTokens": 900
    },
    "costUsd": 0.000868,
    "durationMs": 8388,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.853030303030303,
    "improvement": -0.05555555555555547,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9085858585858585,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:58:51.358Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1759,
      "totalTokens": 3079
    },
    "costUsd": 0.0023748,
    "durationMs": 22404,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T16:57:18.571Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 646,
      "totalTokens": 1915
    },
    "costUsd": 0.001029,
    "durationMs": 10907,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T16:59:02.263Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 2667,
      "totalTokens": 3798
    },
    "costUsd": 0.0034265999999999997,
    "durationMs": 32073,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6666666666666667,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333334,
    "updatedAt": "2026-09-03T16:58:54.492Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 3751,
      "totalTokens": 3865
    },
    "costUsd": 0.004524,
    "durationMs": 44392,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5833333333333334,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.33333333333333337,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-luna",
    "label": "GPT-5.6 Luna",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T16:59:06.474Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 5145,
      "totalTokens": 5208
    },
    "costUsd": 0.0061866,
    "durationMs": 51483,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-03T16:56:02.741Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 5884,
      "totalTokens": 7248
    },
    "costUsd": 0.123136,
    "durationMs": 61290,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.5714285714285714,
    "improvement": -0.1428571428571429,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7142857142857143,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.7944444444444444,
    "updatedAt": "2026-09-03T16:55:44.436Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 8357,
      "totalTokens": 8476
    },
    "costUsd": 0.167616,
    "durationMs": 76830,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.7444444444444445,
    "improvement": -0.04999999999999993,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7944444444444444,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:31.813Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 7113,
      "totalTokens": 7178
    },
    "costUsd": 0.14252,
    "durationMs": 63649,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": -0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:06.740Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 1441,
      "totalTokens": 2643
    },
    "costUsd": 0.033628,
    "durationMs": 27720,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:53:33.181Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 271,
      "totalTokens": 515
    },
    "costUsd": 0.006396,
    "durationMs": 4262,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9177777777777777,
    "updatedAt": "2026-09-03T16:53:42.128Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 1032,
      "totalTokens": 1223
    },
    "costUsd": 0.021404,
    "durationMs": 13427,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9155555555555555,
    "improvement": -0.0022222222222222365,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9377777777777776,
    "skillsImprovement": 0.019999999999999907,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.95,
    "updatedAt": "2026-09-03T16:55:15.759Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 6438,
      "totalTokens": 6655
    },
    "costUsd": 0.129628,
    "durationMs": 62799,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.95,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.95,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8441558441558442,
    "updatedAt": "2026-09-03T16:54:08.644Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 722,
      "totalTokens": 946
    },
    "costUsd": 0.015336,
    "durationMs": 14447,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8917748917748919,
    "improvement": 0.04761904761904767,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8917748917748919,
    "skillsImprovement": 0.04761904761904767,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8478407557354926,
    "updatedAt": "2026-09-03T16:54:02.867Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 1856,
      "totalTokens": 2070
    },
    "costUsd": 0.037976,
    "durationMs": 34165,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.812753036437247,
    "improvement": -0.03508771929824561,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.05341880341880334,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7613636363636365,
    "updatedAt": "2026-09-03T16:54:12.830Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 1616,
      "totalTokens": 1729
    },
    "costUsd": 0.032772,
    "durationMs": 30564,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8545454545454545,
    "improvement": 0.09318181818181803,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8068181818181819,
    "skillsImprovement": 0.045454545454545414,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-03T16:53:56.443Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1399,
      "totalTokens": 1669
    },
    "costUsd": 0.02906,
    "durationMs": 23108,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8808080808080808,
    "updatedAt": "2026-09-03T16:54:16.339Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 1019,
      "totalTokens": 1231
    },
    "costUsd": 0.021228,
    "durationMs": 13333,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.853030303030303,
    "improvement": -0.02777777777777779,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9141414141414143,
    "skillsImprovement": 0.03333333333333344,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:13.127Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1714,
      "totalTokens": 3034
    },
    "costUsd": 0.03956,
    "durationMs": 19175,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T16:53:41.182Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 857,
      "totalTokens": 2126
    },
    "costUsd": 0.022216,
    "durationMs": 12442,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T16:56:10.148Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 6040,
      "totalTokens": 7171
    },
    "costUsd": 0.125324,
    "durationMs": 67359,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.3333333333333333,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5,
    "skillsImprovement": 0.16666666666666669,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.8333333333333334,
    "updatedAt": "2026-09-03T16:55:23.436Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 6414,
      "totalTokens": 6528
    },
    "costUsd": 0.128736,
    "durationMs": 62439,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.8333333333333334,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.16666666666666663,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-sol",
    "label": "GPT-5.6 Sol",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T16:55:14.900Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 5699,
      "totalTokens": 5762
    },
    "costUsd": 0.114232,
    "durationMs": 48745,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.42857142857142855,
    "updatedAt": "2026-09-03T16:57:21.285Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 2881,
      "totalTokens": 4245
    },
    "costUsd": 0.0373,
    "durationMs": 43462,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.5714285714285714,
    "improvement": 0.14285714285714285,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.5714285714285714,
    "skillsImprovement": 0.14285714285714285,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.5166666666666666,
    "updatedAt": "2026-09-03T16:57:30.663Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 5941,
      "totalTokens": 6060
    },
    "costUsd": 0.07153,
    "durationMs": 67830,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.4666666666666667,
    "improvement": -0.04999999999999993,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.5222222222222221,
    "skillsImprovement": 0.005555555555555536,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:57:51.163Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 8034,
      "totalTokens": 8099
    },
    "costUsd": 0.096538,
    "durationMs": 84094,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:57:06.491Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 2211,
      "totalTokens": 3413
    },
    "costUsd": 0.028936,
    "durationMs": 39029,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:34.338Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 248,
      "totalTokens": 492
    },
    "costUsd": 0.003464,
    "durationMs": 3377,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9127777777777777,
    "updatedAt": "2026-09-03T16:55:39.599Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 1246,
      "totalTokens": 1437
    },
    "costUsd": 0.015334,
    "durationMs": 16020,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9105555555555555,
    "improvement": -0.0022222222222222365,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9305555555555556,
    "skillsImprovement": 0.017777777777777892,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9333333333333332,
    "updatedAt": "2026-09-03T16:56:32.719Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 3020,
      "totalTokens": 3237
    },
    "costUsd": 0.036674,
    "durationMs": 32345,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9333333333333332,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333332,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-03T16:55:56.476Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 410,
      "totalTokens": 634
    },
    "costUsd": 0.005368,
    "durationMs": 11770,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8614718614718614,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8917748917748919,
    "skillsImprovement": 0.030303030303030498,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8815789473684211,
    "updatedAt": "2026-09-03T16:55:30.811Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 997,
      "totalTokens": 1211
    },
    "costUsd": 0.012392,
    "durationMs": 17535,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8559379217273954,
    "improvement": -0.025641025641025772,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8478407557354926,
    "skillsImprovement": -0.03373819163292857,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7090909090909091,
    "updatedAt": "2026-09-03T16:56:06.410Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 1304,
      "totalTokens": 1417
    },
    "costUsd": 0.015874,
    "durationMs": 26498,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.634090909090909,
    "improvement": -0.07500000000000007,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8045454545454545,
    "skillsImprovement": 0.09545454545454535,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:47.647Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1044,
      "totalTokens": 1314
    },
    "costUsd": 0.013068,
    "durationMs": 15685,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 0.9166666666666666,
    "improvement": -0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8752525252525253,
    "updatedAt": "2026-09-03T16:56:00.217Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 339,
      "totalTokens": 551
    },
    "costUsd": 0.004492,
    "durationMs": 5151,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.9085858585858585,
    "improvement": 0.033333333333333215,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9419191919191919,
    "skillsImprovement": 0.06666666666666665,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T16:57:02.278Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 2012,
      "totalTokens": 3332
    },
    "costUsd": 0.026784,
    "durationMs": 29395,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T16:55:22.675Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 613,
      "totalTokens": 1882
    },
    "costUsd": 0.009894,
    "durationMs": 7637,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T16:57:44.607Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 4167,
      "totalTokens": 5298
    },
    "costUsd": 0.052266,
    "durationMs": 59001,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.6666666666666666,
    "skillsImprovement": 0.3333333333333333,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333334,
    "updatedAt": "2026-09-03T16:57:07.528Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 4990,
      "totalTokens": 5104
    },
    "costUsd": 0.060108,
    "durationMs": 55319,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5833333333333334,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.41666666666666663,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-5.6-terra",
    "label": "GPT-5.6 Terra",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T16:57:24.598Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 5773,
      "totalTokens": 5836
    },
    "costUsd": 0.069402,
    "durationMs": 69805,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-28T20:37:12.618Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 3170,
      "totalTokens": 4534
    },
    "costUsd": 0.17214,
    "durationMs": 76717,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 1,
    "improvement": 0.1428571428571429,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.1428571428571429,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.7444444444444445,
    "updatedAt": "2026-09-28T20:37:54.367Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 7685,
      "totalTokens": 7804
    },
    "costUsd": 0.38544,
    "durationMs": 161529,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.95,
    "improvement": 0.2055555555555555,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.65,
    "skillsImprovement": -0.09444444444444444,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:40.063Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 3399,
      "totalTokens": 3464
    },
    "costUsd": 0.1706,
    "durationMs": 68009,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:07.473Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 1073,
      "totalTokens": 2275
    },
    "costUsd": 0.06567,
    "durationMs": 32038,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": -0.09090909090909094,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:57.528Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 145,
      "totalTokens": 389
    },
    "costUsd": 0.00969,
    "durationMs": 3372,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9777777777777779,
    "updatedAt": "2026-09-28T20:34:00.081Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 770,
      "totalTokens": 961
    },
    "costUsd": 0.04041,
    "durationMs": 14630,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9555555555555555,
    "improvement": -0.022222222222222365,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333332,
    "skillsImprovement": -0.04444444444444462,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9166666666666667,
    "updatedAt": "2026-09-28T20:36:26.469Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 4836,
      "totalTokens": 5053
    },
    "costUsd": 0.24397,
    "durationMs": 99927,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779222,
    "updatedAt": "2026-09-28T20:34:30.271Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 571,
      "totalTokens": 795
    },
    "costUsd": 0.03079,
    "durationMs": 18173,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8744588744588745,
    "improvement": -0.04761904761904767,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8744588744588745,
    "skillsImprovement": -0.04761904761904767,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8837156995051733,
    "updatedAt": "2026-09-28T20:34:07.686Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 1035,
      "totalTokens": 1249
    },
    "costUsd": 0.05389,
    "durationMs": 28791,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8837156995051733,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.01754385964912264,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7113636363636364,
    "updatedAt": "2026-09-28T20:34:30.676Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 579,
      "totalTokens": 692
    },
    "costUsd": 0.03008,
    "durationMs": 22596,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7818181818181817,
    "improvement": 0.07045454545454533,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8272727272727272,
    "skillsImprovement": 0.11590909090909074,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-28T20:34:37.983Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1724,
      "totalTokens": 1994
    },
    "costUsd": 0.0889,
    "durationMs": 40057,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 0.9166666666666666,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8196969696969697,
    "updatedAt": "2026-09-28T20:34:51.048Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 802,
      "totalTokens": 1014
    },
    "costUsd": 0.04222,
    "durationMs": 20388,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8808080808080808,
    "improvement": 0.061111111111111116,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8474747474747475,
    "skillsImprovement": 0.02777777777777779,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:03.215Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1225,
      "totalTokens": 2545
    },
    "costUsd": 0.07445,
    "durationMs": 27103,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-28T20:33:50.951Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 603,
      "totalTokens": 1872
    },
    "costUsd": 0.04284,
    "durationMs": 11750,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:57.118Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 2481,
      "totalTokens": 3612
    },
    "costUsd": 0.13536,
    "durationMs": 57000,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.9166666666666667,
    "updatedAt": "2026-09-28T20:36:50.242Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 5313,
      "totalTokens": 5427
    },
    "costUsd": 0.26679,
    "durationMs": 113194,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.75,
    "skillsImprovement": -0.16666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-astra",
    "label": "GPT-6 Astra",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:35:59.718Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 2707,
      "totalTokens": 2770
    },
    "costUsd": 0.13598,
    "durationMs": 56083,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-28T20:41:52.670Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 4079,
      "totalTokens": 5443
    },
    "costUsd": 0.0021759,
    "durationMs": 54945,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.2857142857142857,
    "improvement": -0.4285714285714286,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0,
    "skillsImprovement": -0.7142857142857143,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.5166666666666666,
    "updatedAt": "2026-09-28T20:41:41.006Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 5578,
      "totalTokens": 5697
    },
    "costUsd": 0.0028009000000000003,
    "durationMs": 68247,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.3555555555555555,
    "improvement": -0.1611111111111111,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": 0.43333333333333335,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:41:36.883Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 5535,
      "totalTokens": 5600
    },
    "costUsd": 0.002774,
    "durationMs": 58105,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.4,
    "skillsImprovement": -0.6,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:41:39.852Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 2706,
      "totalTokens": 3908
    },
    "costUsd": 0.0014732,
    "durationMs": 44212,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 0.9,
    "updatedAt": "2026-09-28T20:39:38.540Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 336,
      "totalTokens": 580
    },
    "costUsd": 0.00019240000000000001,
    "durationMs": 4544,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 0.9,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.09999999999999998,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9155555555555555,
    "updatedAt": "2026-09-28T20:39:45.055Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 1028,
      "totalTokens": 1219
    },
    "costUsd": 0.0005331,
    "durationMs": 12572,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9555555555555555,
    "improvement": 0.040000000000000036,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9577777777777777,
    "skillsImprovement": 0.04222222222222227,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-28T20:40:55.241Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 4353,
      "totalTokens": 4570
    },
    "costUsd": 0.0021982,
    "durationMs": 48522,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0.01666666666666672,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8441558441558442,
    "updatedAt": "2026-09-28T20:40:04.689Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 1060,
      "totalTokens": 1284
    },
    "costUsd": 0.0005524,
    "durationMs": 19243,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8614718614718614,
    "improvement": 0.017316017316017174,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8614718614718614,
    "skillsImprovement": 0.017316017316017174,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8383940620782727,
    "updatedAt": "2026-09-28T20:39:40.630Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 1854,
      "totalTokens": 2068
    },
    "costUsd": 0.0009484,
    "durationMs": 31215,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8383940620782727,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.06286549707602318,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.5886363636363636,
    "updatedAt": "2026-09-28T20:40:12.560Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 1787,
      "totalTokens": 1900
    },
    "costUsd": 0.0009048,
    "durationMs": 31546,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.6840909090909091,
    "improvement": 0.09545454545454546,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7568181818181818,
    "skillsImprovement": 0.1681818181818182,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-28T20:39:56.138Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1138,
      "totalTokens": 1408
    },
    "costUsd": 0.000596,
    "durationMs": 17551,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 0.9166666666666666,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8752525252525253,
    "updatedAt": "2026-09-28T20:40:04.209Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 625,
      "totalTokens": 837
    },
    "costUsd": 0.0003337,
    "durationMs": 7675,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.791919191919192,
    "improvement": -0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8252525252525252,
    "skillsImprovement": -0.050000000000000044,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:41:20.456Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1840,
      "totalTokens": 3160
    },
    "costUsd": 0.001052,
    "durationMs": 22850,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-28T20:39:23.916Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 656,
      "totalTokens": 1925
    },
    "costUsd": 0.0004549,
    "durationMs": 11437,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-28T20:41:52.966Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 2907,
      "totalTokens": 4038
    },
    "costUsd": 0.0015665999999999998,
    "durationMs": 39200,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.16666666666666666,
    "skillsImprovement": -0.16666666666666666,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.5833333333333334,
    "updatedAt": "2026-09-28T20:41:13.371Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 3735,
      "totalTokens": 3849
    },
    "costUsd": 0.0018789000000000002,
    "durationMs": 46946,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.16666666666666666,
    "skillsImprovement": -0.41666666666666674,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-luna",
    "label": "GPT-6 Luna",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:41:21.990Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 4621,
      "totalTokens": 4684
    },
    "costUsd": 0.0023168000000000004,
    "durationMs": 53938,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-28T20:39:33.597Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 3202,
      "totalTokens": 4566
    },
    "costUsd": 0.034748,
    "durationMs": 52499,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.7142857142857143,
    "improvement": -0.1428571428571428,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.1428571428571429,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.7944444444444444,
    "updatedAt": "2026-09-28T20:39:44.123Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 6225,
      "totalTokens": 6344
    },
    "costUsd": 0.062488,
    "durationMs": 95209,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.8444444444444444,
    "improvement": 0.050000000000000044,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": 0.15555555555555556,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:39:33.006Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 4787,
      "totalTokens": 4852
    },
    "costUsd": 0.048,
    "durationMs": 75619,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:38:57.460Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 1011,
      "totalTokens": 2213
    },
    "costUsd": 0.012514,
    "durationMs": 26300,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:59.413Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 241,
      "totalTokens": 485
    },
    "costUsd": 0.002898,
    "durationMs": 4272,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9355555555555555,
    "updatedAt": "2026-09-28T20:37:06.025Z",
    "tokens": {
      "promptTokens": 191,
      "completionTokens": 1025,
      "totalTokens": 1216
    },
    "costUsd": 0.010632,
    "durationMs": 16210,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9577777777777777,
    "improvement": 0.022222222222222254,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9577777777777777,
    "skillsImprovement": 0.022222222222222254,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.95,
    "updatedAt": "2026-09-28T20:38:30.758Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 3224,
      "totalTokens": 3441
    },
    "costUsd": 0.032674,
    "durationMs": 46153,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9,
    "improvement": -0.04999999999999993,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": -0.033333333333333215,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8744588744588745,
    "updatedAt": "2026-09-28T20:37:25.960Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 532,
      "totalTokens": 756
    },
    "costUsd": 0.005768,
    "durationMs": 12940,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8744588744588745,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8744588744588745,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8580746738641475,
    "updatedAt": "2026-09-28T20:36:49.423Z",
    "tokens": {
      "promptTokens": 214,
      "completionTokens": 903,
      "totalTokens": 1117
    },
    "costUsd": 0.009458,
    "durationMs": 24246,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8559379217273954,
    "improvement": -0.002136752136752129,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.04318488529014841,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.6863636363636364,
    "updatedAt": "2026-09-28T20:37:26.420Z",
    "tokens": {
      "promptTokens": 113,
      "completionTokens": 521,
      "totalTokens": 634
    },
    "costUsd": 0.005436,
    "durationMs": 19973,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.6136363636363636,
    "improvement": -0.07272727272727275,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.6840909090909091,
    "skillsImprovement": -0.002272727272727315,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-28T20:37:22.810Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1323,
      "totalTokens": 1593
    },
    "costUsd": 0.01377,
    "durationMs": 25267,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 0.9166666666666666,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8474747474747475,
    "updatedAt": "2026-09-28T20:37:38.390Z",
    "tokens": {
      "promptTokens": 212,
      "completionTokens": 668,
      "totalTokens": 880
    },
    "costUsd": 0.007104,
    "durationMs": 11558,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8752525252525253,
    "improvement": 0.02777777777777779,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8474747474747475,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:38:52.466Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1068,
      "totalTokens": 2388
    },
    "costUsd": 0.01332,
    "durationMs": 17442,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-28T20:36:39.028Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 645,
      "totalTokens": 1914
    },
    "costUsd": 0.008988,
    "durationMs": 12154,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-28T20:39:32.766Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 2642,
      "totalTokens": 3773
    },
    "costUsd": 0.028682,
    "durationMs": 45735,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": -0.33333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": -0.16666666666666663,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.9166666666666667,
    "updatedAt": "2026-09-28T20:39:14.053Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 4802,
      "totalTokens": 4916
    },
    "costUsd": 0.048248,
    "durationMs": 72163,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": -0.16666666666666674,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333326,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6-sol",
    "label": "GPT-6 Sol",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:39:12.089Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 4606,
      "totalTokens": 4669
    },
    "costUsd": 0.046186,
    "durationMs": 66404,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-03T17:34:07.807Z",
    "tokens": {
      "promptTokens": 1640,
      "completionTokens": 113,
      "totalTokens": 1753
    },
    "costUsd": 0.003958,
    "durationMs": 8210,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.7142857142857143,
    "improvement": 0.7142857142857143,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8571428571428571,
    "skillsImprovement": 0.8571428571428571,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.9,
    "updatedAt": "2026-09-03T17:36:53.322Z",
    "tokens": {
      "promptTokens": 324,
      "completionTokens": 12235,
      "totalTokens": 12559
    },
    "costUsd": 0.074058,
    "durationMs": 188654,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.7388888888888889,
    "improvement": -0.1611111111111111,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.8388888888888889,
    "skillsImprovement": -0.061111111111111116,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Android",
    "category": "Auth",
    "value": 0.2,
    "updatedAt": "2026-09-03T17:33:50.961Z",
    "tokens": {
      "promptTokens": 266,
      "completionTokens": 46,
      "totalTokens": 312
    },
    "costUsd": 0.000808,
    "durationMs": 4581,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.8,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.8,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-03T17:34:05.114Z",
    "tokens": {
      "promptTokens": 1434,
      "completionTokens": 150,
      "totalTokens": 1584
    },
    "costUsd": 0.003768,
    "durationMs": 14015,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 1,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 1,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:31:35.375Z",
    "tokens": {
      "promptTokens": 448,
      "completionTokens": 363,
      "totalTokens": 811
    },
    "costUsd": 0.003074,
    "durationMs": 6002,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 0.3,
    "improvement": -0.7,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9555555555555555,
    "updatedAt": "2026-09-03T17:31:15.648Z",
    "tokens": {
      "promptTokens": 401,
      "completionTokens": 448,
      "totalTokens": 849
    },
    "costUsd": 0.00349,
    "durationMs": 7213,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.8,
    "improvement": -0.15555555555555545,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.63,
    "skillsImprovement": -0.3255555555555555,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.8633333333333333,
    "updatedAt": "2026-09-03T17:33:52.534Z",
    "tokens": {
      "promptTokens": 418,
      "completionTokens": 3382,
      "totalTokens": 3800
    },
    "costUsd": 0.021128,
    "durationMs": 52200,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.6966666666666665,
    "improvement": -0.16666666666666674,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8966666666666667,
    "skillsImprovement": 0.03333333333333344,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-03T17:32:34.418Z",
    "tokens": {
      "promptTokens": 433,
      "completionTokens": 391,
      "totalTokens": 824
    },
    "costUsd": 0.003212,
    "durationMs": 11385,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.8917748917748919,
    "improvement": 0.030303030303030498,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9090909090909092,
    "skillsImprovement": 0.04761904761904778,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.31882591093117413,
    "updatedAt": "2026-09-03T17:31:00.457Z",
    "tokens": {
      "promptTokens": 411,
      "completionTokens": 1147,
      "totalTokens": 1558
    },
    "costUsd": 0.007704,
    "durationMs": 29432,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": 0.5546558704453441,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9269005847953217,
    "skillsImprovement": 0.6080746738641476,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7840909090909092,
    "updatedAt": "2026-09-03T17:32:29.510Z",
    "tokens": {
      "promptTokens": 315,
      "completionTokens": 1276,
      "totalTokens": 1591
    },
    "costUsd": 0.008286,
    "durationMs": 32361,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7568181818181818,
    "improvement": -0.027272727272727337,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7772727272727272,
    "skillsImprovement": -0.006818181818181945,
    "skillsCoverage": "4/4"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-03T17:31:52.805Z",
    "tokens": {
      "promptTokens": 481,
      "completionTokens": 829,
      "totalTokens": 1310
    },
    "costUsd": 0.005936,
    "durationMs": 19524,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8808080808080808,
    "updatedAt": "2026-09-03T17:32:52.376Z",
    "tokens": {
      "promptTokens": 420,
      "completionTokens": 349,
      "totalTokens": 769
    },
    "costUsd": 0.002934,
    "durationMs": 16570,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7696969696969697,
    "improvement": -0.11111111111111116,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9085858585858585,
    "skillsImprovement": 0.02777777777777768,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.3,
    "updatedAt": "2026-09-03T17:33:59.432Z",
    "tokens": {
      "promptTokens": 1567,
      "completionTokens": 147,
      "totalTokens": 1714
    },
    "costUsd": 0.004016,
    "durationMs": 6753,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": 0.5,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.7,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:30:47.674Z",
    "tokens": {
      "promptTokens": 1527,
      "completionTokens": 552,
      "totalTokens": 2079
    },
    "costUsd": 0.006366,
    "durationMs": 14856,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-03T17:34:06.347Z",
    "tokens": {
      "promptTokens": 1358,
      "completionTokens": 115,
      "totalTokens": 1473
    },
    "costUsd": 0.003406,
    "durationMs": 4249,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.6666666666666666,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 1,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.6666666666666667,
    "updatedAt": "2026-09-03T17:35:26.193Z",
    "tokens": {
      "promptTokens": 319,
      "completionTokens": 8527,
      "totalTokens": 8846
    },
    "costUsd": 0.0518,
    "durationMs": 122750,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666667,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.33333333333333326,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.5",
    "label": "Grok 4.5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.2,
    "updatedAt": "2026-09-03T17:33:29.131Z",
    "tokens": {
      "promptTokens": 264,
      "completionTokens": 51,
      "totalTokens": 315
    },
    "costUsd": 0.000834,
    "durationMs": 5497,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0.6000000000000001,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.8,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-03T17:33:46.245Z",
    "tokens": {
      "promptTokens": 1640,
      "completionTokens": 267,
      "totalTokens": 1907
    },
    "costUsd": 0.004882,
    "durationMs": 310055,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0.8571428571428571,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7142857142857143,
    "skillsImprovement": 0.7142857142857143,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.8444444444444444,
    "updatedAt": "2026-09-04T03:56:23.586Z",
    "tokens": {
      "promptTokens": 324,
      "completionTokens": 32916,
      "totalTokens": 33240
    },
    "costUsd": 0.198144,
    "durationMs": 474871,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.8444444444444444,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.8944444444444444,
    "skillsImprovement": 0.04999999999999993,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:32:01.602Z",
    "tokens": {
      "promptTokens": 266,
      "completionTokens": 17416,
      "totalTokens": 17682
    },
    "costUsd": 0.105028,
    "durationMs": 253715,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:29:37.059Z",
    "tokens": {
      "promptTokens": 1434,
      "completionTokens": 5914,
      "totalTokens": 7348
    },
    "costUsd": 0.038352,
    "durationMs": 104605,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:24:28.494Z",
    "tokens": {
      "promptTokens": 448,
      "completionTokens": 882,
      "totalTokens": 1330
    },
    "costUsd": 0.006188,
    "durationMs": 12712,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9355555555555555,
    "updatedAt": "2026-09-03T17:24:49.593Z",
    "tokens": {
      "promptTokens": 401,
      "completionTokens": 3122,
      "totalTokens": 3523
    },
    "costUsd": 0.019534,
    "durationMs": 41483,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9555555555555555,
    "improvement": 0.020000000000000018,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9527777777777778,
    "skillsImprovement": 0.01722222222222236,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-03T17:28:36.059Z",
    "tokens": {
      "promptTokens": 418,
      "completionTokens": 11750,
      "totalTokens": 12168
    },
    "costUsd": 0.071336,
    "durationMs": 169321,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9333333333333332,
    "improvement": 0.033333333333333215,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8966666666666667,
    "skillsImprovement": -0.0033333333333332993,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.5887445887445887,
    "updatedAt": "2026-09-03T17:25:44.952Z",
    "tokens": {
      "promptTokens": 433,
      "completionTokens": 2310,
      "totalTokens": 2743
    },
    "costUsd": 0.014726,
    "durationMs": 43860,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9220779220779222,
    "improvement": 0.3333333333333335,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9220779220779222,
    "skillsImprovement": 0.3333333333333335,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.4726720647773279,
    "updatedAt": "2026-09-03T17:24:50.273Z",
    "tokens": {
      "promptTokens": 411,
      "completionTokens": 3369,
      "totalTokens": 3780
    },
    "costUsd": 0.021036,
    "durationMs": 67150,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8559379217273954,
    "improvement": 0.38326585695006743,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9012595591542959,
    "skillsImprovement": 0.42858749437696797,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7795454545454545,
    "updatedAt": "2026-09-03T17:25:46.602Z",
    "tokens": {
      "promptTokens": 315,
      "completionTokens": 3035,
      "totalTokens": 3350
    },
    "costUsd": 0.01884,
    "durationMs": 56199,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7545454545454545,
    "improvement": -0.025000000000000022,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7295454545454545,
    "skillsImprovement": -0.050000000000000044,
    "skillsCoverage": "4/4"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:24:52.542Z",
    "tokens": {
      "promptTokens": 481,
      "completionTokens": 1941,
      "totalTokens": 2422
    },
    "costUsd": 0.012608,
    "durationMs": 34606,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8808080808080808,
    "updatedAt": "2026-09-03T17:26:18.156Z",
    "tokens": {
      "promptTokens": 420,
      "completionTokens": 3890,
      "totalTokens": 4310
    },
    "costUsd": 0.02418,
    "durationMs": 51081,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8808080808080808,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9085858585858585,
    "skillsImprovement": 0.02777777777777768,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:30:30.849Z",
    "tokens": {
      "promptTokens": 1567,
      "completionTokens": 8868,
      "totalTokens": 10435
    },
    "costUsd": 0.056342,
    "durationMs": 136777,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 0.8,
    "improvement": -0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-03T17:24:07.969Z",
    "tokens": {
      "promptTokens": 1527,
      "completionTokens": 1345,
      "totalTokens": 2872
    },
    "costUsd": 0.011124,
    "durationMs": 21375,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8235294117647058,
    "improvement": -0.17647058823529416,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-03T17:34:01.970Z",
    "tokens": {
      "promptTokens": 1358,
      "completionTokens": 168,
      "totalTokens": 1526
    },
    "costUsd": 0.003724,
    "durationMs": 307296,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": 0.6666666666666666,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.8333333333333334,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.6666666666666666,
    "updatedAt": "2026-09-04T04:00:51.105Z",
    "tokens": {
      "promptTokens": 319,
      "completionTokens": 17818,
      "totalTokens": 18137
    },
    "costUsd": 0.107546,
    "durationMs": 267526,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.5833333333333334,
    "improvement": -0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0.2500000000000001,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.6",
    "label": "Grok 4.6",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.4,
    "updatedAt": "2026-09-03T18:34:44.320Z",
    "tokens": {
      "promptTokens": 264,
      "completionTokens": 91,
      "totalTokens": 355
    },
    "durationMs": 6555,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0.4,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-28T21:01:17.591Z",
    "tokens": {
      "promptTokens": 2676,
      "completionTokens": 55682,
      "totalTokens": 58358
    },
    "costUsd": 0.339444,
    "durationMs": 628809,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0,
    "improvement": -0.8571428571428571,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.1428571428571429,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.788888888888889,
    "updatedAt": "2026-09-28T20:57:16.207Z",
    "tokens": {
      "promptTokens": 1360,
      "completionTokens": 47940,
      "totalTokens": 49300
    },
    "costUsd": 0.29036,
    "durationMs": 542470,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.4444444444444444,
    "improvement": -0.34444444444444455,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": 0.16111111111111098,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Android",
    "category": "Auth",
    "value": 0.4,
    "updatedAt": "2026-09-28T20:50:28.554Z",
    "tokens": {
      "promptTokens": 1302,
      "completionTokens": 68,
      "totalTokens": 1370
    },
    "costUsd": 0.003012,
    "durationMs": 4721,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0.4,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.6,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0,
    "updatedAt": "2026-09-28T20:50:41.040Z",
    "tokens": {
      "promptTokens": 2470,
      "completionTokens": 285,
      "totalTokens": 2755
    },
    "costUsd": 0.00665,
    "durationMs": 12094,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 1,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 1,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 0,
    "updatedAt": "2026-09-28T20:41:56.238Z",
    "tokens": {
      "promptTokens": 1484,
      "completionTokens": 196,
      "totalTokens": 1680
    },
    "costUsd": 0.004144,
    "durationMs": 3171,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 1,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 1,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.7777777777777778,
    "updatedAt": "2026-09-28T20:42:29.201Z",
    "tokens": {
      "promptTokens": 1437,
      "completionTokens": 3794,
      "totalTokens": 5231
    },
    "costUsd": 0.025638,
    "durationMs": 41817,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9777777777777779,
    "improvement": 0.20000000000000007,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 1,
    "skillsImprovement": 0.2222222222222222,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.7666666666666667,
    "updatedAt": "2026-09-28T20:50:23.437Z",
    "tokens": {
      "promptTokens": 1454,
      "completionTokens": 29181,
      "totalTokens": 30635
    },
    "costUsd": 0.177994,
    "durationMs": 364821,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0.15000000000000002,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8833333333333334,
    "skillsImprovement": 0.1166666666666667,
    "skillsCoverage": "5/5"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-28T20:47:22.703Z",
    "tokens": {
      "promptTokens": 1469,
      "completionTokens": 20370,
      "totalTokens": 21839
    },
    "costUsd": 0.125158,
    "durationMs": 277048,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.5757575757575758,
    "improvement": -0.2857142857142856,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.6363636363636364,
    "skillsImprovement": -0.22510822510822504,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.551731893837157,
    "updatedAt": "2026-09-28T20:42:43.618Z",
    "tokens": {
      "promptTokens": 1447,
      "completionTokens": 6084,
      "totalTokens": 7531
    },
    "costUsd": 0.039398,
    "durationMs": 81230,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8734817813765182,
    "improvement": 0.3217498875393612,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9188034188034188,
    "skillsImprovement": 0.3670715249662617,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.6840909090909091,
    "updatedAt": "2026-09-28T20:44:07.325Z",
    "tokens": {
      "promptTokens": 1351,
      "completionTokens": 7471,
      "totalTokens": 8822
    },
    "costUsd": 0.047528,
    "durationMs": 95045,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7568181818181818,
    "improvement": 0.07272727272727275,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.7318181818181818,
    "skillsImprovement": 0.04772727272727273,
    "skillsCoverage": "4/4"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-28T20:44:18.214Z",
    "tokens": {
      "promptTokens": 1517,
      "completionTokens": 10872,
      "totalTokens": 12389
    },
    "costUsd": 0.068266,
    "durationMs": 144864,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7696969696969697,
    "updatedAt": "2026-09-28T20:45:34.768Z",
    "tokens": {
      "promptTokens": 1456,
      "completionTokens": 8005,
      "totalTokens": 9461
    },
    "costUsd": 0.050942,
    "durationMs": 90929,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8196969696969697,
    "improvement": 0.050000000000000044,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9141414141414143,
    "skillsImprovement": 0.1444444444444446,
    "skillsCoverage": "3/3"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "React",
    "category": "Add Auth",
    "value": 0.3,
    "updatedAt": "2026-09-28T20:50:48.372Z",
    "tokens": {
      "promptTokens": 2603,
      "completionTokens": 305,
      "totalTokens": 2908
    },
    "costUsd": 0.007036,
    "durationMs": 6939,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0.7,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.7,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-28T20:41:56.251Z",
    "tokens": {
      "promptTokens": 2563,
      "completionTokens": 1492,
      "totalTokens": 4055
    },
    "costUsd": 0.014078,
    "durationMs": 18977,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0.17647058823529416,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.17647058823529416,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.6666666666666666,
    "updatedAt": "2026-09-28T20:59:32.133Z",
    "tokens": {
      "promptTokens": 2394,
      "completionTokens": 41316,
      "totalTokens": 43710
    },
    "costUsd": 0.252684,
    "durationMs": 472422,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 1,
    "improvement": 0.33333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.16666666666666674,
    "skillsCoverage": "1/1"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.75,
    "updatedAt": "2026-09-28T20:55:53.422Z",
    "tokens": {
      "promptTokens": 1355,
      "completionTokens": 51567,
      "totalTokens": 52922
    },
    "costUsd": 0.312112,
    "durationMs": 592011,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.9166666666666667,
    "improvement": 0.16666666666666674,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.5833333333333334,
    "skillsImprovement": -0.16666666666666663,
    "skillsCoverage": "2/2"
  },
  {
    "model": "grok-4.7",
    "label": "Grok 4.7",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-28T20:54:25.635Z",
    "tokens": {
      "promptTokens": 1300,
      "completionTokens": 32814,
      "totalTokens": 34114
    },
    "costUsd": 0.199484,
    "durationMs": 422524,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-28T20-19-41-899Z",
    "provider": "x-ai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-28T20-19-41-899Z"],
      "mcpRunIds": ["mcp-2026-09-28T21-14-23-875Z"],
      "skillsRunIds": ["skills-2026-09-28T21-52-07-254Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.7142857142857143,
    "updatedAt": "2026-09-03T18:00:08.019Z",
    "tokens": {
      "promptTokens": 1379,
      "completionTokens": 18208,
      "totalTokens": 19587
    },
    "costUsd": 0.046688294,
    "durationMs": 244822,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.7142857142857143,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8571428571428571,
    "skillsImprovement": 0.1428571428571428,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.4611111111111111,
    "updatedAt": "2026-09-03T18:00:29.708Z",
    "tokens": {
      "promptTokens": 131,
      "completionTokens": 14798,
      "totalTokens": 14929
    },
    "costUsd": 0.03711905199999999,
    "durationMs": 480090,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z", "2026-09-03T19-03-19-970Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.7277777777777779,
    "improvement": 0.2666666666666668,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7944444444444444,
    "skillsImprovement": 0.3333333333333333,
    "skillsCoverage": "2/2"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:57:55.786Z",
    "tokens": {
      "promptTokens": 76,
      "completionTokens": 19442,
      "totalTokens": 19518
    },
    "costUsd": 0.048687826,
    "durationMs": 286798,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 0.8,
    "improvement": -0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": -0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:56:17.733Z",
    "tokens": {
      "promptTokens": 1223,
      "completionTokens": 11953,
      "totalTokens": 13176
    },
    "costUsd": 0.030914434999999997,
    "durationMs": 165191,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": -0.09090909090909094,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:43:40.026Z",
    "tokens": {
      "promptTokens": 253,
      "completionTokens": 3460,
      "totalTokens": 3713
    },
    "costUsd": 0.008864462,
    "durationMs": 58180,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9305555555555556,
    "updatedAt": "2026-09-03T17:44:01.144Z",
    "tokens": {
      "promptTokens": 207,
      "completionTokens": 7153,
      "totalTokens": 7360
    },
    "costUsd": 0.018062290999999998,
    "durationMs": 109671,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.8883333333333333,
    "improvement": -0.04222222222222227,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 1,
    "skillsImprovement": 0.06944444444444442,
    "skillsCoverage": "5/5"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-03T19:08:17.693Z",
    "tokens": {
      "promptTokens": 235,
      "completionTokens": 22145,
      "totalTokens": 22380
    },
    "costUsd": 0.055580634999999996,
    "durationMs": 296730,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T19-03-19-994Z",
    "provider": "tencent",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T19-03-19-994Z", "2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.9,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8833333333333334,
    "skillsImprovement": -0.016666666666666607,
    "skillsCoverage": "5/5"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779222,
    "updatedAt": "2026-09-03T17:45:51.504Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 5299,
      "totalTokens": 5543
    },
    "costUsd": 0.013456294999999998,
    "durationMs": 89928,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9393939393939394,
    "improvement": 0.017316017316017285,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8917748917748919,
    "skillsImprovement": -0.030303030303030276,
    "skillsCoverage": "3/3"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8734817813765182,
    "updatedAt": "2026-09-03T17:43:29.909Z",
    "tokens": {
      "promptTokens": 224,
      "completionTokens": 10244,
      "totalTokens": 10468
    },
    "costUsd": 0.025807059999999996,
    "durationMs": 165062,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8221997300944669,
    "improvement": -0.05128205128205132,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8499775078722447,
    "skillsImprovement": -0.023504273504273532,
    "skillsCoverage": "3/3"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7568181818181818,
    "updatedAt": "2026-09-03T17:53:08.854Z",
    "tokens": {
      "promptTokens": 126,
      "completionTokens": 17588,
      "totalTokens": 17714
    },
    "costUsd": 0.044092672,
    "durationMs": 568696,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.8545454545454545,
    "improvement": 0.09772727272727266,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8522727272727273,
    "skillsImprovement": 0.09545454545454546,
    "skillsCoverage": "4/4"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:46:54.649Z",
    "tokens": {
      "promptTokens": 278,
      "completionTokens": 14811,
      "totalTokens": 15089
    },
    "costUsd": 0.037274163,
    "durationMs": 222266,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.7419191919191919,
    "updatedAt": "2026-09-03T17:48:45.591Z",
    "tokens": {
      "promptTokens": 229,
      "completionTokens": 11441,
      "totalTokens": 11670
    },
    "costUsd": 0.028804927,
    "durationMs": 173958,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.7863636363636363,
    "improvement": 0.0444444444444444,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.7893939393939394,
    "skillsImprovement": 0.04747474747474756,
    "skillsCoverage": "3/3"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:56:03.057Z",
    "tokens": {
      "promptTokens": 1340,
      "completionTokens": 11433,
      "totalTokens": 12773
    },
    "costUsd": 0.029711493,
    "durationMs": 149827,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-03T17:42:11.295Z",
    "tokens": {
      "promptTokens": 1294,
      "completionTokens": 6861,
      "totalTokens": 8155
    },
    "costUsd": 0.018238557,
    "durationMs": 83100,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.7647058823529411,
    "improvement": -0.05882352941176472,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.3333333333333333,
    "updatedAt": "2026-09-03T18:03:59.667Z",
    "tokens": {
      "promptTokens": 1154,
      "completionTokens": 11019,
      "totalTokens": 12173
    },
    "costUsd": 0.028520955,
    "durationMs": 461790,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.3333333333333333,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0.5,
    "skillsCoverage": "1/1"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.6666666666666667,
    "updatedAt": "2026-09-04T04:27:15.862Z",
    "tokens": {
      "promptTokens": 125,
      "completionTokens": 35958,
      "totalTokens": 36083
    },
    "costUsd": 0.090035208,
    "durationMs": 618905,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.6666666666666666,
    "improvement": -1.1102230246251565e-16,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.4166666666666667,
    "skillsImprovement": -0.25000000000000006,
    "skillsCoverage": "2/2"
  },
  {
    "model": "hy4-preview",
    "label": "Tencent Hy4 Preview",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:51:04.010Z",
    "tokens": {
      "promptTokens": 74,
      "completionTokens": 7004,
      "totalTokens": 7078
    },
    "costUsd": 0.017578720000000003,
    "durationMs": 93703,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "tencent",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 1,
    "improvement": 0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Android",
    "category": "Add Auth",
    "value": 0.8571428571428571,
    "updatedAt": "2026-09-03T17:42:25.462Z",
    "tokens": {
      "promptTokens": 1399,
      "completionTokens": 13413,
      "totalTokens": 14812
    },
    "costUsd": 0.205392,
    "durationMs": 168458,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 0.8571428571428571,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.7142857142857143,
    "skillsImprovement": -0.1428571428571428,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.788888888888889,
    "updatedAt": "2026-09-03T19:08:09.287Z",
    "tokens": {
      "promptTokens": 205,
      "completionTokens": 23642,
      "totalTokens": 23847
    },
    "costUsd": 0.355245,
    "durationMs": 288260,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-03T19-03-19-966Z",
    "provider": "moonshotai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T19-03-19-966Z", "2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.6833333333333333,
    "improvement": -0.10555555555555562,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.7444444444444445,
    "skillsImprovement": -0.04444444444444451,
    "skillsCoverage": "2/2"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:46:37.872Z",
    "tokens": {
      "promptTokens": 150,
      "completionTokens": 13008,
      "totalTokens": 13158
    },
    "costUsd": 0.19557,
    "durationMs": 456208,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 0.8,
    "improvement": -0.19999999999999996,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:40:08.569Z",
    "tokens": {
      "promptTokens": 1236,
      "completionTokens": 3767,
      "totalTokens": 5003
    },
    "costUsd": 0.060213,
    "durationMs": 59364,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:35:35.658Z",
    "tokens": {
      "promptTokens": 322,
      "completionTokens": 1505,
      "totalTokens": 1827
    },
    "costUsd": 0.023541,
    "durationMs": 22254,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9555555555555555,
    "updatedAt": "2026-09-03T17:35:32.017Z",
    "tokens": {
      "promptTokens": 274,
      "completionTokens": 3502,
      "totalTokens": 3776
    },
    "costUsd": 0.053352,
    "durationMs": 52100,
    "evaluationPath": "evals/auth/passkey-sign-in",
    "evalKey": "evals/auth/passkey-sign-in",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/auth/passkey-sign-in",
        "evals/auth/protect",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/routes",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 1,
    "improvement": 0.04444444444444451,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9777777777777779,
    "skillsImprovement": 0.022222222222222365,
    "skillsCoverage": "5/5"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.85,
    "updatedAt": "2026-09-03T17:40:44.719Z",
    "tokens": {
      "promptTokens": 299,
      "completionTokens": 19805,
      "totalTokens": 20104
    },
    "costUsd": 0.297972,
    "durationMs": 215098,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization",
        "evals/billing/subscriptions-webhook"
      ]
    },
    "mcpScore": 0.8833333333333334,
    "improvement": 0.03333333333333344,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.8666666666666666,
    "skillsImprovement": 0.016666666666666607,
    "skillsCoverage": "5/5"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.8614718614718614,
    "updatedAt": "2026-09-03T17:37:42.810Z",
    "tokens": {
      "promptTokens": 309,
      "completionTokens": 6265,
      "totalTokens": 6574
    },
    "costUsd": 0.094902,
    "durationMs": 94011,
    "evaluationPath": "evals/organizations/membership-webhook",
    "evalKey": "evals/organizations/membership-webhook",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task",
        "evals/organizations/url-sync"
      ]
    },
    "mcpScore": 0.9220779220779222,
    "improvement": 0.060606060606060774,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8614718614718614,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8221997300944669,
    "updatedAt": "2026-09-03T17:34:47.250Z",
    "tokens": {
      "promptTokens": 297,
      "completionTokens": 2670,
      "totalTokens": 2967
    },
    "costUsd": 0.040941,
    "durationMs": 39306,
    "evaluationPath": "evals/quickstarts/keyless",
    "evalKey": "evals/quickstarts/keyless",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/keyless", "evals/quickstarts/nextjs", "evals/quickstarts/nextjs-app-router"]
    },
    "mcpScore": 0.8221997300944669,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8221997300944669,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.8045454545454545,
    "updatedAt": "2026-09-03T17:36:50.125Z",
    "tokens": {
      "promptTokens": 197,
      "completionTokens": 4111,
      "totalTokens": 4308
    },
    "costUsd": 0.062256,
    "durationMs": 62039,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-button-menu",
        "evals/ui-components/user-profile-embed"
      ]
    },
    "mcpScore": 0.7863636363636364,
    "improvement": -0.018181818181818077,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.875,
    "skillsImprovement": 0.07045454545454555,
    "skillsCoverage": "4/4"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-03T17:36:08.657Z",
    "tokens": {
      "promptTokens": 346,
      "completionTokens": 2839,
      "totalTokens": 3185
    },
    "costUsd": 0.043623,
    "durationMs": 42315,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8171717171717172,
    "updatedAt": "2026-09-03T17:37:20.012Z",
    "tokens": {
      "promptTokens": 296,
      "completionTokens": 1611,
      "totalTokens": 1907
    },
    "costUsd": 0.025053,
    "durationMs": 26554,
    "evaluationPath": "evals/webhooks/notifications",
    "evalKey": "evals/webhooks/notifications",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/webhooks/notifications", "evals/webhooks/user-created", "evals/webhooks/user-sync"]
    },
    "mcpScore": 0.8505050505050505,
    "improvement": 0.033333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.7419191919191919,
    "skillsImprovement": -0.07525252525252535,
    "skillsCoverage": "3/3"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-03T17:40:03.407Z",
    "tokens": {
      "promptTokens": 1354,
      "completionTokens": 4020,
      "totalTokens": 5374
    },
    "costUsd": 0.064362,
    "durationMs": 51910,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-03T17:34:20.129Z",
    "tokens": {
      "promptTokens": 1350,
      "completionTokens": 1005,
      "totalTokens": 2355
    },
    "costUsd": 0.019125,
    "durationMs": 11208,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.7647058823529411,
    "improvement": -0.05882352941176472,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8823529411764706,
    "skillsImprovement": 0.05882352941176472,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.6666666666666666,
    "updatedAt": "2026-09-03T17:42:17.157Z",
    "tokens": {
      "promptTokens": 1168,
      "completionTokens": 9743,
      "totalTokens": 10911
    },
    "costUsd": 0.149649,
    "durationMs": 135225,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 1,
    "improvement": 0.33333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.33333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.6666666666666667,
    "updatedAt": "2026-09-03T17:41:24.005Z",
    "tokens": {
      "promptTokens": 200,
      "completionTokens": 19169,
      "totalTokens": 19369
    },
    "costUsd": 0.288135,
    "durationMs": 211634,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": 0.08333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 1,
    "skillsImprovement": 0.33333333333333326,
    "skillsCoverage": "2/2"
  },
  {
    "model": "kimi-k3",
    "label": "Kimi K3",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-03T17:39:01.457Z",
    "tokens": {
      "promptTokens": 148,
      "completionTokens": 6685,
      "totalTokens": 6833
    },
    "costUsd": 0.100719,
    "durationMs": 64728,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-03T16-53-28-385Z",
    "provider": "moonshotai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-03T16-53-28-385Z"],
      "mcpRunIds": ["mcp-2026-09-03T19-08-33-670Z"],
      "skillsRunIds": ["skills-2026-09-03T20-20-09-441Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-29T17:18:31.706Z",
    "tokens": {
      "promptTokens": 1794,
      "completionTokens": 1946,
      "totalTokens": 3740
    },
    "costUsd": 0.023048,
    "durationMs": 23008,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": -0.09090909090909094,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-29T17:17:19.057Z",
    "tokens": {
      "promptTokens": 194,
      "completionTokens": 15514,
      "totalTokens": 15708
    },
    "costUsd": 0.155528,
    "durationMs": 91694,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.95,
    "improvement": -0.050000000000000044,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.95,
    "skillsImprovement": -0.050000000000000044,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Android",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-29T17:16:40.367Z",
    "tokens": {
      "promptTokens": 2137,
      "completionTokens": 3329,
      "totalTokens": 5466
    },
    "costUsd": 0.037564,
    "durationMs": 31839,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-29T17:16:37.234Z",
    "tokens": {
      "promptTokens": 99,
      "completionTokens": 8228,
      "totalTokens": 8327
    },
    "costUsd": 0.082478,
    "durationMs": 46197,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8,
    "skillsImprovement": -0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 0.8333333333333334,
    "updatedAt": "2026-09-29T17:16:25.497Z",
    "tokens": {
      "promptTokens": 1739,
      "completionTokens": 2310,
      "totalTokens": 4049
    },
    "costUsd": 0.026578,
    "durationMs": 16972,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.5,
    "improvement": -0.33333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8333333333333334,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-29T17:16:19.247Z",
    "tokens": {
      "promptTokens": 1969,
      "completionTokens": 2287,
      "totalTokens": 4256
    },
    "costUsd": 0.026808,
    "durationMs": 16943,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-29T17:16:18.817Z",
    "tokens": {
      "promptTokens": 94,
      "completionTokens": 8034,
      "totalTokens": 8128
    },
    "costUsd": 0.080528,
    "durationMs": 46475,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.9166666666666667,
    "updatedAt": "2026-09-29T17:16:08.394Z",
    "tokens": {
      "promptTokens": 184,
      "completionTokens": 5984,
      "totalTokens": 6168
    },
    "costUsd": 0.060208,
    "durationMs": 36694,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.8333333333333334,
    "improvement": -0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.9,
    "updatedAt": "2026-09-29T17:16:02.175Z",
    "tokens": {
      "promptTokens": 354,
      "completionTokens": 7730,
      "totalTokens": 8084
    },
    "costUsd": 0.078008,
    "durationMs": 43603,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/subscriptions-webhook",
        "evals/billing/checkout-new",
        "evals/billing/feature-authorization",
        "evals/billing/events-webhook"
      ]
    },
    "mcpScore": 0.8800000000000001,
    "improvement": -0.019999999999999907,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9523809523809524,
    "updatedAt": "2026-09-29T17:15:47.234Z",
    "tokens": {
      "promptTokens": 223,
      "completionTokens": 7159,
      "totalTokens": 7382
    },
    "costUsd": 0.072036,
    "durationMs": 46501,
    "evaluationPath": "evals/organizations/url-sync",
    "evalKey": "evals/organizations/url-sync",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": [
        "evals/organizations/url-sync",
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task"
      ]
    },
    "mcpScore": 0.8917748917748917,
    "improvement": -0.060606060606060774,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.9523809523809524,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8116161616161616,
    "updatedAt": "2026-09-29T17:15:32.222Z",
    "tokens": {
      "promptTokens": 180,
      "completionTokens": 2376,
      "totalTokens": 2556
    },
    "costUsd": 0.02412,
    "durationMs": 22949,
    "evaluationPath": "evals/webhooks/user-created",
    "evalKey": "evals/webhooks/user-created",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/webhooks/user-created", "evals/webhooks/user-sync", "evals/webhooks/notifications"]
    },
    "mcpScore": 0.8171717171717172,
    "improvement": 0.005555555555555647,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.883838383838384,
    "skillsImprovement": 0.07222222222222241,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7340909090909091,
    "updatedAt": "2026-09-29T17:15:29.409Z",
    "tokens": {
      "promptTokens": 170,
      "completionTokens": 4424,
      "totalTokens": 4594
    },
    "costUsd": 0.04458,
    "durationMs": 37591,
    "evaluationPath": "evals/ui-components/organization-switcher",
    "evalKey": "evals/ui-components/organization-switcher",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": [
        "evals/ui-components/organization-switcher",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/user-profile-embed",
        "evals/ui-components/user-button-menu"
      ]
    },
    "mcpScore": 0.8090909090909091,
    "improvement": 0.07499999999999996,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8522727272727273,
    "skillsImprovement": 0.11818181818181817,
    "skillsCoverage": "4/4"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8756185335132703,
    "updatedAt": "2026-09-29T17:15:15.995Z",
    "tokens": {
      "promptTokens": 1607,
      "completionTokens": 1509,
      "totalTokens": 3116
    },
    "costUsd": 0.018304,
    "durationMs": 31869,
    "evaluationPath": "evals/quickstarts/nextjs-app-router",
    "evalKey": "evals/quickstarts/nextjs-app-router",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/quickstarts/nextjs-app-router", "evals/quickstarts/keyless", "evals/quickstarts/nextjs"]
    },
    "mcpScore": 0.8756185335132703,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8756185335132703,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9777777777777779,
    "updatedAt": "2026-09-29T17:15:14.922Z",
    "tokens": {
      "promptTokens": 225,
      "completionTokens": 3666,
      "totalTokens": 3891
    },
    "costUsd": 0.03711,
    "durationMs": 30806,
    "evaluationPath": "evals/auth/routes",
    "evalKey": "evals/auth/routes",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": [
        "evals/auth/routes",
        "evals/auth/protect",
        "evals/auth/passkey-sign-in",
        "evals/auth/setup-mfa-task",
        "evals/auth/reverification-sensitive-action"
      ]
    },
    "mcpScore": 0.9777777777777779,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9777777777777779,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "User Management",
    "value": 1,
    "updatedAt": "2026-09-29T17:15:09.142Z",
    "tokens": {
      "promptTokens": 424,
      "completionTokens": 2667,
      "totalTokens": 3091
    },
    "costUsd": 0.027518,
    "durationMs": 20747,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "React",
    "category": "Quickstarts",
    "value": 0.8235294117647058,
    "updatedAt": "2026-09-29T17:14:51.679Z",
    "tokens": {
      "promptTokens": 2144,
      "completionTokens": 924,
      "totalTokens": 3068
    },
    "costUsd": 0.013528,
    "durationMs": 7564,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 0.8235294117647058,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.8235294117647058,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "claude-sonnet-5-5",
    "label": "Claude Sonnet 5.5",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-29T17:14:49.909Z",
    "tokens": {
      "promptTokens": 371,
      "completionTokens": 676,
      "totalTokens": 1047
    },
    "costUsd": 0.007502,
    "durationMs": 5762,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-29T17-14-43-949Z",
    "provider": "anthropic",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-29T17-14-43-949Z"],
      "mcpRunIds": ["mcp-2026-09-29T17-18-45-311Z"],
      "skillsRunIds": ["skills-2026-09-29T17-21-28-444Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "iOS",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-30T02:54:55.569Z",
    "tokens": {
      "promptTokens": 1131,
      "completionTokens": 2306,
      "totalTokens": 3437
    },
    "costUsd": 0.025322,
    "durationMs": 43443,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::ios",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/add-auth::ios"]
    },
    "mcpScore": 0.8333333333333334,
    "improvement": -0.16666666666666663,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Android",
    "category": "Quickstarts",
    "value": 0.7,
    "updatedAt": "2026-09-30T02:47:50.798Z",
    "tokens": {
      "promptTokens": 119,
      "completionTokens": 5790,
      "totalTokens": 5909
    },
    "costUsd": 0.058138,
    "durationMs": 95148,
    "evaluationPath": "evals/android/custom-setup",
    "evalKey": "evals/android/custom-setup",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/android/custom-setup", "evals/android/prebuilt-setup"]
    },
    "mcpScore": 0.95,
    "improvement": 0.25,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.75,
    "skillsImprovement": 0.050000000000000044,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Android",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-30T02:47:40.767Z",
    "tokens": {
      "promptTokens": 1364,
      "completionTokens": 2462,
      "totalTokens": 3826
    },
    "costUsd": 0.027348,
    "durationMs": 50212,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::android",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/add-auth::android"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Android",
    "category": "Auth",
    "value": 1,
    "updatedAt": "2026-09-30T02:47:19.690Z",
    "tokens": {
      "promptTokens": 65,
      "completionTokens": 3588,
      "totalTokens": 3653
    },
    "costUsd": 0.03601,
    "durationMs": 61086,
    "evaluationPath": "evals/android/routing",
    "evalKey": "evals/android/routing",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/android/routing"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "React",
    "category": "Add Auth",
    "value": 1,
    "updatedAt": "2026-09-30T02:47:06.608Z",
    "tokens": {
      "promptTokens": 1320,
      "completionTokens": 1096,
      "totalTokens": 2416
    },
    "costUsd": 0.0136,
    "durationMs": 21792,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::react",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/add-auth::react"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Add Auth",
    "value": 0.9090909090909091,
    "updatedAt": "2026-09-30T02:46:57.497Z",
    "tokens": {
      "promptTokens": 1202,
      "completionTokens": 1020,
      "totalTokens": 2222
    },
    "costUsd": 0.012604,
    "durationMs": 27084,
    "evaluationPath": "evals/add-auth",
    "evalKey": "evals/add-auth::nextjs",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/add-auth::nextjs"]
    },
    "mcpScore": 0.9090909090909091,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 0.9090909090909091,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "iOS",
    "category": "Auth",
    "value": 0.8,
    "updatedAt": "2026-09-30T02:46:50.985Z",
    "tokens": {
      "promptTokens": 63,
      "completionTokens": 3861,
      "totalTokens": 3924
    },
    "costUsd": 0.038736,
    "durationMs": 56421,
    "evaluationPath": "evals/ios/routing",
    "evalKey": "evals/ios/routing",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/ios/routing"]
    },
    "mcpScore": 0.8,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.19999999999999996,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Billing",
    "value": 0.95,
    "updatedAt": "2026-09-30T02:46:50.410Z",
    "tokens": {
      "promptTokens": 217,
      "completionTokens": 4821,
      "totalTokens": 5038
    },
    "costUsd": 0.048644,
    "durationMs": 74142,
    "evaluationPath": "evals/billing/checkout-existing",
    "evalKey": "evals/billing/checkout-existing",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": [
        "evals/billing/checkout-existing",
        "evals/billing/checkout-new",
        "evals/billing/subscriptions-webhook",
        "evals/billing/events-webhook",
        "evals/billing/feature-authorization"
      ]
    },
    "mcpScore": 0.9166666666666666,
    "improvement": -0.033333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9166666666666666,
    "skillsImprovement": -0.033333333333333326,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "iOS",
    "category": "Quickstarts",
    "value": 0.9166666666666667,
    "updatedAt": "2026-09-30T02:46:44.674Z",
    "tokens": {
      "promptTokens": 114,
      "completionTokens": 3625,
      "totalTokens": 3739
    },
    "costUsd": 0.036478,
    "durationMs": 55054,
    "evaluationPath": "evals/ios/custom-setup",
    "evalKey": "evals/ios/custom-setup",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 2,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/ios/custom-setup", "evals/ios/prebuilt-setup"]
    },
    "mcpScore": 0.75,
    "improvement": -0.16666666666666674,
    "toolsUsed": [],
    "mcpCoverage": "2/2",
    "skillsScore": 0.9166666666666667,
    "skillsImprovement": 0,
    "skillsCoverage": "2/2"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Organizations",
    "value": 0.9220779220779219,
    "updatedAt": "2026-09-30T02:46:18.478Z",
    "tokens": {
      "promptTokens": 143,
      "completionTokens": 3551,
      "totalTokens": 3694
    },
    "costUsd": 0.035796,
    "durationMs": 59478,
    "evaluationPath": "evals/organizations/url-sync",
    "evalKey": "evals/organizations/url-sync",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": [
        "evals/organizations/url-sync",
        "evals/organizations/membership-webhook",
        "evals/organizations/onboarding-task"
      ]
    },
    "mcpScore": 0.9220779220779219,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8744588744588745,
    "skillsImprovement": -0.04761904761904745,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Webhooks",
    "value": 0.8474747474747475,
    "updatedAt": "2026-09-30T02:46:01.672Z",
    "tokens": {
      "promptTokens": 117,
      "completionTokens": 1609,
      "totalTokens": 1726
    },
    "costUsd": 0.016324,
    "durationMs": 33770,
    "evaluationPath": "evals/webhooks/user-created",
    "evalKey": "evals/webhooks/user-created",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/webhooks/user-created", "evals/webhooks/user-sync", "evals/webhooks/notifications"]
    },
    "mcpScore": 0.8808080808080808,
    "improvement": 0.033333333333333326,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8474747474747475,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "UI Components",
    "value": 0.7340909090909091,
    "updatedAt": "2026-09-30T02:45:45.519Z",
    "tokens": {
      "promptTokens": 89,
      "completionTokens": 1243,
      "totalTokens": 1332
    },
    "costUsd": 0.012608,
    "durationMs": 35390,
    "evaluationPath": "evals/ui-components/user-profile-embed",
    "evalKey": "evals/ui-components/user-profile-embed",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 4,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": [
        "evals/ui-components/user-profile-embed",
        "evals/ui-components/sign-in-customization",
        "evals/ui-components/organization-switcher",
        "evals/ui-components/user-button-menu"
      ]
    },
    "mcpScore": 0.7363636363636363,
    "improvement": 0.002272727272727204,
    "toolsUsed": [],
    "mcpCoverage": "4/4",
    "skillsScore": 0.8272727272727272,
    "skillsImprovement": 0.09318181818181803,
    "skillsCoverage": "4/4"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Quickstarts",
    "value": 0.8837156995051733,
    "updatedAt": "2026-09-30T02:45:35.816Z",
    "tokens": {
      "promptTokens": 1005,
      "completionTokens": 723,
      "totalTokens": 1728
    },
    "costUsd": 0.00924,
    "durationMs": 36847,
    "evaluationPath": "evals/quickstarts/nextjs-app-router",
    "evalKey": "evals/quickstarts/nextjs-app-router",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 3,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/quickstarts/nextjs-app-router", "evals/quickstarts/keyless", "evals/quickstarts/nextjs"]
    },
    "mcpScore": 0.8837156995051733,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "3/3",
    "skillsScore": 0.8837156995051733,
    "skillsImprovement": 0,
    "skillsCoverage": "3/3"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "User Management",
    "value": 0.9166666666666666,
    "updatedAt": "2026-09-30T02:45:30.249Z",
    "tokens": {
      "promptTokens": 270,
      "completionTokens": 1495,
      "totalTokens": 1765
    },
    "costUsd": 0.01549,
    "durationMs": 28309,
    "evaluationPath": "evals/user-management/profile-page",
    "evalKey": "evals/user-management/profile-page",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/user-management/profile-page"]
    },
    "mcpScore": 1,
    "improvement": 0.08333333333333337,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0.08333333333333337,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Auth",
    "value": 0.9333333333333332,
    "updatedAt": "2026-09-30T02:45:28.150Z",
    "tokens": {
      "promptTokens": 156,
      "completionTokens": 1340,
      "totalTokens": 1496
    },
    "costUsd": 0.013712,
    "durationMs": 29184,
    "evaluationPath": "evals/auth/routes",
    "evalKey": "evals/auth/routes",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 5,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": [
        "evals/auth/routes",
        "evals/auth/protect",
        "evals/auth/passkey-sign-in",
        "evals/auth/reverification-sensitive-action",
        "evals/auth/setup-mfa-task"
      ]
    },
    "mcpScore": 0.9333333333333332,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "5/5",
    "skillsScore": 0.9333333333333332,
    "skillsImprovement": 0,
    "skillsCoverage": "5/5"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "React",
    "category": "Quickstarts",
    "value": 1,
    "updatedAt": "2026-09-30T02:45:09.999Z",
    "tokens": {
      "promptTokens": 1269,
      "completionTokens": 524,
      "totalTokens": 1793
    },
    "costUsd": 0.007778,
    "durationMs": 11044,
    "evaluationPath": "evals/quickstarts/react-vite",
    "evalKey": "evals/quickstarts/react-vite",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/quickstarts/react-vite"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  },
  {
    "model": "gpt-6.1-sol",
    "label": "GPT-6.1 Sol",
    "framework": "Next.js",
    "category": "Machine Auth",
    "value": 1,
    "updatedAt": "2026-09-30T02:45:01.828Z",
    "tokens": {
      "promptTokens": 244,
      "completionTokens": 145,
      "totalTokens": 389
    },
    "costUsd": 0.001938,
    "durationMs": 2829,
    "evaluationPath": "evals/auth/machine-tokens",
    "evalKey": "evals/auth/machine-tokens",
    "runId": "2026-09-30T02-44-58-795Z",
    "provider": "openai",
    "evalsRun": 1,
    "provenance": {
      "baseRunIds": ["2026-09-30T02-44-58-795Z"],
      "mcpRunIds": ["mcp-2026-09-30T02-48-04-042Z"],
      "skillsRunIds": ["skills-2026-09-30T02-51-36-770Z"],
      "evalKeys": ["evals/auth/machine-tokens"]
    },
    "mcpScore": 1,
    "improvement": 0,
    "toolsUsed": [],
    "mcpCoverage": "1/1",
    "skillsScore": 1,
    "skillsImprovement": 0,
    "skillsCoverage": "1/1"
  }
]
