{"slug":"benchmark","source_name":"benchmark","name":"Benchmark","description":"Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":45.5,"total_cases":22,"passed_cases":10,"tokens_delta_pct":1.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-07-27T16:12:16.578652+00:00"},"skill_score":0.4545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":45.5,"without_pass_pct":4.5,"tokens_delta_pct":1.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-07-27T16:12:16.578652+00:00","run_id":"52e02dce-85b2-434d-9762-9542a7855590","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":null,"content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"78de8318f680752e94804a0588df3dcadb6027c9333e0bd6bffbd6d331b0f33e","raw_url":"https://app.decimal.ai/s/benchmark/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/benchmark"}