{"slug":"affaan-m-agent-self-evaluation","source_name":"affaan-m/agent-self-evaluation","name":"Affaan M/Agent Self Evaluation","description":"Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.","version":1,"lift":{"pass_rate_delta_pts":50,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":99.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T10:24:07.755101+00:00"},"skill_score":0.7727,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":50,"with_pass_pct":77.3,"without_pass_pct":27.3,"tokens_delta_pct":99.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-03T10:24:07.755101+00:00","run_id":"4e94edda-39ef-4cd0-b441-970fb225f056","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":"d802884c5a7b93b071faa068b8ad037e57f42c28d0978eb294e4c7a038a0d748","raw_url":"https://app.decimal.ai/s/affaan-m-agent-self-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/affaan-m-agent-self-evaluation"}