{"slug":"microck-llm-evaluation","source_name":"microck/llm-evaluation","name":"Microck/LLM Evaluation","description":"Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.","version":1,"lift":{"pass_rate_delta_pts":0,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":146.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-21T04:18:53.744781+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":0,"with_pass_pct":81.8,"without_pass_pct":81.8,"tokens_delta_pct":146.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-21T04:18:53.744781+00:00","run_id":"5ccc5205-b92f-426f-8560-bc9539047578","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"NOASSERTION","install_count":0,"manifest_hash":"300b0641b16252cd6c190f1d6d4864ef204271a4780816ae9975d91f4ce5773b","raw_url":"https://app.decimal.ai/s/microck-llm-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/microck-llm-evaluation"}