{"slug":"borghei-agentic-evaluation-framework","source_name":"borghei/agentic-evaluation-framework","name":"Borghei/Agentic Evaluation Framework","description":"This skill should be used when the user asks to \"evaluate LLM output quality\", \"set up LLM-as-judge\", \"build an eval rubric\", \"compare model outputs pairwise\", or \"measure agent quality\".","version":1,"lift":{"pass_rate_delta_pts":30.43,"pass_rate_pct":82.6,"total_cases":23,"passed_cases":19,"tokens_delta_pct":47.4,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-20T06:48:03.421161+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":30.43,"with_pass_pct":82.6,"without_pass_pct":52.2,"tokens_delta_pct":47.4,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-20T06:48:03.421161+00:00","run_id":"7d5100a1-3d85-4d8c-a202-adb57506dee0","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 + Commons Clause","install_count":0,"manifest_hash":"901fdfdf2e12e3c9579471806fd17888c3133ab690735b949b82a01bdf4f8028","raw_url":"https://app.decimal.ai/s/borghei-agentic-evaluation-framework/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/borghei-agentic-evaluation-framework"}