{"slug":"sickn33-llm-evaluation","source_name":"sickn33/llm-evaluation","name":"Sickn33/LLM Evaluation","description":"Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.","version":1,"lift":{"pass_rate_delta_pts":41.67,"pass_rate_pct":79.2,"total_cases":24,"passed_cases":19,"tokens_delta_pct":141.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-28T23:11:17.419670+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":41.67,"with_pass_pct":79.2,"without_pass_pct":37.5,"tokens_delta_pct":141.3,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":24,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-28T23:11:17.419670+00:00","run_id":"b31d3dd9-3869-4d0d-83a5-60033ad283ec","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":"MIT","install_count":0,"manifest_hash":"0bece336a0f28a671794ac95cc2e6142d48784cd4fab24e403c6efbad3908a69","raw_url":"https://app.decimal.ai/s/sickn33-llm-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/sickn33-llm-evaluation"}