{"slug":"dicklesworthstone-llm-evaluation","source_name":"dicklesworthstone/llm-evaluation","name":"Dicklesworthstone/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":18.18,"pass_rate_pct":63.6,"total_cases":22,"passed_cases":14,"tokens_delta_pct":146.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-29T05:17:09.502193+00:00"},"skill_score":0.6364,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":63.6,"without_pass_pct":45.5,"tokens_delta_pct":146.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-29T05:17:09.502193+00:00","run_id":"8cc2be16-86e9-49c7-9324-4f1abc71357a","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":"2b8e52ae3f5e0db051a3dde421cdc2317603e108d864c23f760b983ddc140d4f","raw_url":"https://app.decimal.ai/s/dicklesworthstone-llm-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/dicklesworthstone-llm-evaluation"}