skills/validate-idea/_scores.json

{
  "version": "1.0.0",
  "skillHash": "sha256:83902341b47fdd5c1e6a71b9bdb97f5e2ccc3a0cec93d7ecf5c91ec89cf62e0d",
  "scoredAt": "2026-05-13T10:33:11.600Z",
  "backend": "subagent",
  "model": "claude-sonnet-4-6",
  "quality": {
    "score": 100,
    "dimensions": {
      "clarity": "PASS",
      "completeness": "PASS",
      "conciseness": "PASS",
      "actionability": "PASS",
      "crossPlatform": "PASS",
      "examples": "PASS"
    },
    "issues": []
  },
  "security": {
    "verdict": "SAFE",
    "issues": []
  },
  "impact": {
    "baselineAvg": 33,
    "treatmentAvg": 95,
    "multiplier": 2.88,
    "scenarios": [
      {
        "name": "SaaS idea evaluation (LinkedIn outreach automation)",
        "baseline": 30,
        "treatment": 95,
        "rationale": "Baseline recommends building an MVP after light competitor research and a TAM analysis without demanding manual processizing or naming 10 specific people; treatment defines the precise ICP, demands current workaround and 10/3 conversation thresholds, applies processize-manually-first, calls out red flags, and ends with a Needs-more-validation verdict and manual-first next steps."
      },
      {
        "name": "Niche tool idea (team Pomodoro for remote workers)",
        "baseline": 35,
        "treatment": 95,
        "rationale": "Baseline suggests waitlists, surveys, and a 2-week MVP without rejecting friends-as-validation or pushing manual sales; treatment names red flags (friends-cool, not-in-community, no existing workarounds), demands 10 named people and 3 paid manual customers, and delivers a Pivot verdict with concrete manual-first steps."
      }
    ]
  }
}