{"slug":"boshu2-skill-eval","source_name":"boshu2/skill-eval","name":"Boshu2/Skill Eval","description":"Author and tier behavioral probes for a Triggers: \"measure this skill\", \"the probe came back INERT\", \"the control arm aces it\", \"harden this scenario\", \"is this skill actually doing anything\".","version":5,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":123,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-10-10T14:26:24.352020+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":95.5,"without_pass_pct":59.1,"tokens_delta_pct":123,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-10-10T14:26:24.352020+00:00","run_id":"72b0614d-62cb-47f4-8029-c5d49ea8dcc3","latest_attempt":{"id":"72b0614d-62cb-47f4-8029-c5d49ea8dcc3","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-10-10T14:26:24.352020+00:00","gate":null},"version_number":4,"is_latest_version":false,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"total_uses":0,"total_users":0,"manifest_hash":"cb30b2ca0362c3a2e30d375ccd7e376852b39b9322af6c0bc503da5bc46bc9ff","install_name":"boshu2-skill-eval","version_id":"46be55cb-f3e5-430b-b2fd-fc952f8bacb8","body_sha256":"cb30b2ca0362c3a2e30d375ccd7e376852b39b9322af6c0bc503da5bc46bc9ff","render_hash":"3cd94d03729158cb30106f3728b204009d05b636100e654885e49e617fdac048","raw_url":"https://app.decimal.ai/s/boshu2-skill-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/boshu2-skill-eval"}