{"slug":"alirezarezvani-self-eval","source_name":"alirezarezvani/self-eval","name":"Alirezarezvani/Self Eval","description":"Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.","version":1,"lift":{"pass_rate_delta_pts":59.09,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":70.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-11T10:38:00.216330+00:00"},"skill_score":0.7727,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":59.09,"with_pass_pct":77.3,"without_pass_pct":18.2,"tokens_delta_pct":70.4,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-11T10:38:00.216330+00:00","run_id":"4463de5b-1755-490e-a0b9-1dbf10cc11c0","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":"101582c9fa3d510987f13c689e2cbce37990aa44ae2668ab0859f29902f7c132","raw_url":"https://app.decimal.ai/s/alirezarezvani-self-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/alirezarezvani-self-eval"}