skills/aws-ses/_scores.json

{
  "version": "1.0.0",
  "skillHash": "sha256:b075c74216001bca274b733951476aa6df9062937922826945751f449e55d95c",
  "scoredAt": "2026-05-13T14:27:49.402Z",
  "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 AWS SES operations."
      }
    ]
  },
  "security": {
    "verdict": "SAFE",
    "issues": []
  },
  "impact": {
    "multiplier": 10,
    "baselineAvg": 0,
    "treatmentAvg": 100,
    "scenarios": [
      {
        "name": "verify-domain-dkim",
        "baseline": 0,
        "treatment": 100,
        "rationale": "Response A includes the exact sesv2 commands required by the rubric, while Response B uses different SES commands and does not meet the rubric requirements."
      },
      {
        "name": "setup-receipt-rule-s3-lambda",
        "baseline": 0,
        "treatment": 100,
        "rationale": "Response A exactly matches the required command and JSON structure, while Response B uses a different rule set name, rule name, bucket, and Lambda ARN, failing to meet the rubric."
      }
    ]
  }
}