skills/aws-ec2/_scores.json

{
  "version": "1.0.0",
  "skillHash": "sha256:aedaee1f737df0b730ba669adb8b1b0d35fa028681f67828294773294dea4c62",
  "scoredAt": "2026-05-13T14:24:32.375Z",
  "backend": "ollama",
  "model": "gpt-oss:20b",
  "quality": {
    "score": 93,
    "dimensions": {
      "clarity": "PASS",
      "completeness": "WEAK",
      "conciseness": "PASS",
      "actionability": "PASS",
      "crossPlatform": "PASS",
      "examples": "PASS"
    },
    "issues": [
      {
        "severity": "MEDIUM",
        "category": "completeness",
        "detail": "The skill does not cover error handling or edge cases for EC2 operations."
      }
    ]
  },
  "security": {
    "verdict": "SAFE",
    "issues": []
  },
  "impact": {
    "multiplier": 1.37,
    "baselineAvg": 73,
    "treatmentAvg": 100,
    "scenarios": [
      {
        "name": "launch-instance-with-user-data",
        "baseline": 100,
        "treatment": 100,
        "rationale": "Both responses include all required flags and details specified in the rubric."
      },
      {
        "name": "setup-auto-scaling-group-with-launch-template",
        "baseline": 45,
        "treatment": 100,
        "rationale": "Response A fully satisfies all rubric requirements, while Response B omits critical details and uses incorrect commands."
      }
    ]
  }
}