{"slug":"advanced-evaluation","source_name":"advanced-evaluation","name":"Advanced Evaluation","description":"This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.","version":1,"lift":{"pass_rate_delta_pts":34.78,"pass_rate_pct":34.8,"total_cases":23,"passed_cases":8,"tokens_delta_pct":106.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-07-27T20:58:22.063416+00:00"},"skill_score":0.3679,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":34.78,"with_pass_pct":34.8,"without_pass_pct":0,"tokens_delta_pct":106.5,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-07-27T20:58:22.063416+00:00","run_id":"2a122c71-b7d1-4aa3-80b5-cc37ad039861","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 License","install_count":0,"manifest_hash":"921482c3681a6960f69bbffe6bc74dd0e9aafa080d456aa50888796f999626cd","raw_url":"https://app.decimal.ai/s/advanced-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/advanced-evaluation"}