{"slug":"miosa-osa-eval-rag","source_name":"miosa-osa/eval-rag","name":"Miosa Osa/Eval RAG","description":"Evaluate retrieval and generation quality in RAG pipelines. Separate scoring for retrieval (recall, precision, MRR) and generation (faithfulness, relevance, completeness). End-to-end pipeline assessment with bottleneck identification. Triggers on: \"eval rag\", \"rag evaluation\", \"retrieval evaluation\", \"rag quality\", \"rag metrics\"","version":1,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":28.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-27T08:40:01.430500+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":95.5,"without_pass_pct":59.1,"tokens_delta_pct":28.8,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":18,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-27T08:40:01.430500+00:00","run_id":"d0ea8a05-4518-4a54-9965-3639067bcf8f","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":null,"install_count":0,"manifest_hash":"64c0a2ee9e698c24f41b14ced9e7e2fc0360512944b61cd3605993235d0e0c36","raw_url":"https://app.decimal.ai/s/miosa-osa-eval-rag/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/miosa-osa-eval-rag"}