skills/artillery/_scores.json

{
  "version": "1.0.0",
  "skillHash": "sha256:254e7fa0fa2d88ff98ce01405116cd221bfa6f1aeefa119a258b3931b744a599",
  "scoredAt": "2026-05-13T14:13:45.309Z",
  "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 beyond the happy path."
      }
    ]
  },
  "security": {
    "verdict": "SAFE",
    "issues": []
  },
  "impact": {
    "multiplier": 10,
    "baselineAvg": 5,
    "treatmentAvg": 100,
    "scenarios": [
      {
        "name": "http-ecommerce-load-test",
        "baseline": 10,
        "treatment": 100,
        "rationale": "Response B fully satisfies all rubric requirements, while Response A is incomplete and does not meet the specified YAML structure."
      },
      {
        "name": "websocket-chat-test",
        "baseline": 0,
        "treatment": 100,
        "rationale": "Response A fully satisfies the rubric with a correct YAML structure, while Response B provides a Node.js script instead of the required YAML test scenario."
      }
    ]
  }
}