{"slug":"majiayu000-advanced-evaluation","source_name":"majiayu000/advanced-evaluation","name":"Majiayu000/Advanced Evaluation","description":"This skill should be used when the user asks to \"implement LLM-as-judge\", \"compare model outputs\", \"create evaluation rubrics\", \"mitigate evaluation bias\", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.","version":4,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":136.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T05:28:16.496041+00:00"},"skill_score":0.9545,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":95.5,"without_pass_pct":77.3,"tokens_delta_pct":136.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T05:28:16.496041+00:00","run_id":"fe48c27d-4501-419b-bc87-b7bf2daa6c23","latest_attempt":{"id":"fe48c27d-4501-419b-bc87-b7bf2daa6c23","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T05:28:16.496041+00:00","gate":null},"version_number":4,"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,"total_uses":0,"total_users":0,"manifest_hash":"194ba0878d304c18385a4a7b3c6610e3377b9638a9717eb1a7d908cdefefed18","install_name":"majiayu000-advanced-evaluation","version_id":"dd4d1121-b922-43d9-99ac-876f0d50436c","body_sha256":"194ba0878d304c18385a4a7b3c6610e3377b9638a9717eb1a7d908cdefefed18","render_hash":"de9fe6c5b125e89db004dd8db8e89d9e4cf1301ff42ac3db76588b59e51b6bee","raw_url":"https://app.decimal.ai/s/majiayu000-advanced-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/majiayu000-advanced-evaluation"}