{"slug":"yogsoth-ai-benchmark-archaeology","source_name":"yogsoth-ai/benchmark-archaeology","name":"Yogsoth AI/Benchmark Archaeology","description":"Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.","version":2,"lift":{"pass_rate_delta_pts":null,"pass_rate_pct":27.3,"total_cases":22,"passed_cases":6,"tokens_delta_pct":35.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T03:36:34.957533+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":false,"delta_pts":null,"with_pass_pct":null,"without_pass_pct":null,"tokens_delta_pct":35.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":7,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-22T03:36:34.957533+00:00","run_id":"42c8d395-aec9-43d7-aa09-8926727cf468","version_number":2,"is_latest_version":true,"gate":"underpowered"}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"c776f64066f562d6a1f0fd59d0b6c3d3ade1f228ec0e67588f14cb70e5e4890f","raw_url":"https://app.decimal.ai/s/yogsoth-ai-benchmark-archaeology/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-benchmark-archaeology"}