{"slug":"xu-xiang-eval-harness","source_name":"xu-xiang/eval-harness","name":"Xu Xiang/Eval Harness","description":"为 Claude Code 会话提供的正式评测框架，实现了评测驱动开发（EDD）原则","version":4,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":33.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-12T05:25:44.287609+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":86.4,"without_pass_pct":50,"tokens_delta_pct":33.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-12T05:25:44.287609+00:00","run_id":"bf1640e6-74a4-4931-ab81-ee885ed30e89","version_number":4,"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":"8a2b821379e40062fbd9cc9b16ab9d07f3f41d8b53d219ebaf9676775c35b33a","raw_url":"https://app.decimal.ai/s/xu-xiang-eval-harness/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/xu-xiang-eval-harness"}