{"slug":"pramoddutta-rag-regression-testing","source_name":"pramoddutta/RAG Regression Testing","name":"Pramoddutta/RAG Regression Testing","description":"Gate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.","version":1,"lift":{"pass_rate_delta_pts":31.82,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":115.2,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-19T00:04:00.556600+00:00"},"skill_score":0.7412,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":31.82,"with_pass_pct":95.5,"without_pass_pct":63.6,"tokens_delta_pct":115.2,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-19T00:04:00.556600+00:00","run_id":"104856b4-1680-4d50-8c40-e85e460e4f1a","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":"852555207599e327a5bebf30ae073a67f69fb2cd5cf86991d6082c333c07baa6","raw_url":"https://app.decimal.ai/s/pramoddutta-rag-regression-testing/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/pramoddutta-rag-regression-testing"}