{"slug":"phoenix-evals","source_name":"phoenix-evals","name":"Phoenix Evals","description":"Build and run evaluators for AI/LLM applications using Phoenix.","version":2,"lift":{"pass_rate_delta_pts":13.64,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":24,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-08T15:37:54.549562+00:00"},"skill_score":0.8288,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":13.64,"with_pass_pct":95.5,"without_pass_pct":81.8,"tokens_delta_pct":24,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-08T15:37:54.549562+00:00","run_id":"19b1796c-3f4c-4040-ac92-9f512124c51d","version_number":2,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":6,"manifest_hash":"3b3f5c2ab56d7bc48ca493e9699fb0c5e3a5b98dfa56cfadf8af987224a139cc","raw_url":"https://app.decimal.ai/s/phoenix-evals/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/phoenix-evals"}