{"slug":"loulanyue-eval-harness","source_name":"loulanyue/eval-harness","name":"Loulanyue/Eval Harness","description":"Claude Codeセッションの正式な評価フレームワークで、評価駆動開発（EDD）の原則を実装します","version":6,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":20.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-22T05:55:19.118661+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":95.5,"without_pass_pct":54.5,"tokens_delta_pct":20.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-22T05:55:19.118661+00:00","run_id":"f78fa503-72c5-4b58-9391-44366af5d40d","version_number":6,"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":"cf74ab755ef2f00657fbca186996f60f138396106b2761699280faa9f3826bbb","raw_url":"https://app.decimal.ai/s/loulanyue-eval-harness/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/loulanyue-eval-harness"}