{"slug":"arize-evaluator","source_name":"arize-evaluator","name":"Arize Evaluator","description":"Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.","version":1,"lift":{"pass_rate_delta_pts":63.64,"pass_rate_pct":63.6,"total_cases":22,"passed_cases":14,"tokens_delta_pct":376.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-07-24T10:12:24.018265+00:00"},"skill_score":0.6364,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":63.64,"with_pass_pct":63.6,"without_pass_pct":0,"tokens_delta_pct":376.6,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":18,"verdict":"mixed","never_hurt":false,"completed_at":"2026-07-24T10:12:24.018265+00:00","run_id":"0fdc5d88-ff4f-4c15-bd3d-d23ad7e847dd","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":"bc158d681cb2905389ba5babba9ccb2eb6d2645ce03627dbf9a725928b5baf3e","raw_url":"https://app.decimal.ai/s/arize-evaluator/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/arize-evaluator"}