{"slug":"bagelhole-rag-observability-evals","source_name":"bagelhole/rag-observability-evals","name":"Bagelhole/RAG Observability Evals","description":"Monitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.","version":1,"lift":{"pass_rate_delta_pts":36.36,"pass_rate_pct":77.3,"total_cases":22,"passed_cases":17,"tokens_delta_pct":145.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-19T01:30:58.576868+00:00"},"skill_score":0.8794055555555556,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":36.36,"with_pass_pct":77.3,"without_pass_pct":40.9,"tokens_delta_pct":145.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-19T01:30:58.576868+00:00","run_id":"00b57474-08f6-4ec6-bd61-d7b10ef9e58c","latest_attempt":{"id":"00b57474-08f6-4ec6-bd61-d7b10ef9e58c","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-19T01:30:58.576868+00:00","gate":null},"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":1,"total_uses":103,"total_users":5,"manifest_hash":"121c7055892196b9ce52f9260e46dcfb648dacad058d6a9b60234dc67f1b9d4d","install_name":"bagelhole-rag-observability-evals","version_id":"884b22b4-5d56-4d8c-bb30-548d282dc195","body_sha256":"121c7055892196b9ce52f9260e46dcfb648dacad058d6a9b60234dc67f1b9d4d","render_hash":"d03bb4dc13d9b26587d8e15622016adf4925ce35528c5db89635704a32f5b56b","raw_url":"https://app.decimal.ai/s/bagelhole-rag-observability-evals/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/bagelhole-rag-observability-evals"}