{"slug":"agent-performance-benchmarker","source_name":"agent-performance-benchmarker","name":"Agent Performance Benchmarker","description":"Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":54.5,"total_cases":22,"passed_cases":12,"tokens_delta_pct":228.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-07-28T14:35:41.222758+00:00"},"skill_score":0.5455,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":54.5,"without_pass_pct":13.6,"tokens_delta_pct":228.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":21,"verdict":"mixed","never_hurt":false,"completed_at":"2026-07-28T14:35:41.222758+00:00","run_id":"1b524f75-9107-4aa3-a219-4eef5bb95ab7","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":"6eb58bde6ac99a00b73d314e5c5df9c344373540d29766dc2c56ff9b96b1f5e1","raw_url":"https://app.decimal.ai/s/agent-performance-benchmarker/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agent-performance-benchmarker"}