{ "_comment": "EXAMPLE data so the leaderboard renders before you run real evals. Replace by running: ANTHROPIC_API_KEY=... node evals/run-evals.mjs", "example": true, "generatedAt": "2026-06-18T00:00:00.000Z", "judge": "claude-opus-4-8", "models": ["claude-sonnet-4-6", "claude-haiku-4-5-20251001"], "dimensions": ["structure", "completeness", "usefulness", "grounding"], "results": [ { "skill": "rice-prioritisation", "model": "claude-sonnet-4-6", "scores": {"structure":5,"completeness":5,"usefulness":5,"grounding":4}, "overall": 4.75 }, { "skill": "rice-prioritisation", "model": "claude-haiku-4-5-20251001", "scores": {"structure":5,"completeness":4,"usefulness":4,"grounding":4}, "overall": 4.25 }, { "skill": "prd-template", "model": "claude-sonnet-4-6", "scores": {"structure":5,"completeness":4,"usefulness":5,"grounding":4}, "overall": 4.5 }, { "skill": "prd-template", "model": "claude-haiku-4-5-20251001", "scores": {"structure":4,"completeness":4,"usefulness":4,"grounding":4}, "overall": 4.0 }, { "skill": "cs-health-scorecard", "model": "claude-sonnet-4-6", "scores": {"structure":5,"completeness":5,"usefulness":5,"grounding":5}, "overall": 5.0 }, { "skill": "cs-health-scorecard", "model": "claude-haiku-4-5-20251001", "scores": {"structure":5,"completeness":4,"usefulness":4,"grounding":4}, "overall": 4.25 }, { "skill": "executive-summary", "model": "claude-sonnet-4-6", "scores": {"structure":5,"completeness":5,"usefulness":4,"grounding":5}, "overall": 4.75 }, { "skill": "executive-summary", "model": "claude-haiku-4-5-20251001", "scores": {"structure":5,"completeness":4,"usefulness":4,"grounding":5}, "overall": 4.5 }, { "skill": "competitive-analysis", "model": "claude-sonnet-4-6", "scores": {"structure":4,"completeness":4,"usefulness":5,"grounding":4}, "overall": 4.25 }, { "skill": "competitive-analysis", "model": "claude-haiku-4-5-20251001", "scores": {"structure":4,"completeness":4,"usefulness":4,"grounding":4}, "overall": 4.0 }, { "skill": "sprint-planning", "model": "claude-sonnet-4-6", "scores": {"structure":5,"completeness":5,"usefulness":5,"grounding":5}, "overall": 5.0 }, { "skill": "sprint-planning", "model": "claude-haiku-4-5-20251001", "scores": {"structure":5,"completeness":4,"usefulness":4,"grounding":5}, "overall": 4.5 } ] }