skills/auth-system-setup/_scores.json

{
  "version": "1.0.0",
  "skillHash": "sha256:ad8f23725eb7ee0365d190358a0219a5776c7e4a362867601a15550ad8a44c96",
  "scoredAt": "2026-05-13T14:18:54.805Z",
  "backend": "ollama",
  "model": "gpt-oss:20b",
  "quality": {
    "score": 87,
    "dimensions": {
      "clarity": "PASS",
      "completeness": "WEAK",
      "conciseness": "PASS",
      "actionability": "WEAK",
      "crossPlatform": "PASS",
      "examples": "PASS"
    },
    "issues": [
      {
        "severity": "MEDIUM",
        "category": "completeness",
        "detail": "The instructions do not cover all possible error scenarios and edge cases, such as network failures or provider-specific errors."
      },
      {
        "severity": "MEDIUM",
        "category": "actionability",
        "detail": "The skill provides high-level guidance and example outputs but lacks concrete, runnable code snippets or step-by-step procedures."
      }
    ]
  },
  "security": {
    "verdict": "SAFE",
    "issues": []
  },
  "impact": {
    "multiplier": 1.6,
    "baselineAvg": 50,
    "treatmentAvg": 80,
    "scenarios": [
      {
        "name": "express-google-oauth-jwt",
        "baseline": 50,
        "treatment": 80,
        "rationale": "Response A covers the required migration, PKCE OAuth, JWT service, middleware, and mentions tests, while Response B lacks the migration, refresh token rotation, and test coverage."
      },
      {
        "name": "django-github-multi-tenant-rbac",
        "baseline": 50,
        "treatment": 80,
        "rationale": "Response A covers most rubric items (models, migration, middleware, decorator) but lacks django‑allauth integration; Response B omits middleware, decorator, tests, and migration, making it less complete."
      }
    ]
  }
}