{"slug":"archive228-self-eval-bias","source_name":"archive228/self-eval-bias","name":"Archive228/Self Eval Bias","description":"Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.","version":1,"lift":{"pass_rate_delta_pts":27.27,"pass_rate_pct":72.7,"total_cases":22,"passed_cases":16,"tokens_delta_pct":4.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-16T00:47:04.921836+00:00"},"skill_score":0.7273,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":27.27,"with_pass_pct":72.7,"without_pass_pct":45.5,"tokens_delta_pct":4.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-16T00:47:04.921836+00:00","run_id":"43af8ff5-f5f9-493e-a781-1fb70689206d","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":"MIT","install_count":0,"manifest_hash":"6377711bf5f5d7c3451da9cce8b0f7236ab7c87acd891e8cdea18b6b78a5291c","raw_url":"https://app.decimal.ai/s/archive228-self-eval-bias/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/archive228-self-eval-bias"}