{"slug":"yogsoth-ai-benchmark-audit","source_name":"yogsoth-ai/benchmark-audit","name":"Yogsoth AI/Benchmark Audit","description":"Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches","version":1,"lift":{"pass_rate_delta_pts":45.45,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":3.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T03:41:36.931486+00:00"},"skill_score":0.7727,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":45.45,"with_pass_pct":77.3,"without_pass_pct":31.8,"tokens_delta_pct":3.4,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":18,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-22T03:41:36.931486+00:00","run_id":"9a1c4c52-5ee5-4863-b2c3-91090b07dae5","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"42e35b2b566e969d05100b12d9b49ab5e78b5a6364fb3b50b26c09a1ed05b9b4","raw_url":"https://app.decimal.ai/s/yogsoth-ai-benchmark-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/yogsoth-ai-benchmark-audit"}