{"slug":"agentscope-ai-rag-eval","source_name":"agentscope-ai/rag-eval","name":"Agentscope AI/RAG Eval","description":"Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or \"is my RAG pipeline working.\" Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.","version":1,"lift":{"pass_rate_delta_pts":20.83,"pass_rate_pct":83.3,"total_cases":24,"passed_cases":20,"tokens_delta_pct":67.7,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-15T02:53:06.238484+00:00"},"skill_score":0.8333,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":20.83,"with_pass_pct":83.3,"without_pass_pct":62.5,"tokens_delta_pct":67.7,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":24,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-15T02:53:06.238484+00:00","run_id":"0d0c9669-9dbc-4aa7-b2da-74d27adbe281","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":"Apache-2.0","install_count":1,"manifest_hash":"95e10dfaae0122ac416a9d956bef5ad8cf2455192d29213b490cb2402c697b92","raw_url":"https://app.decimal.ai/s/agentscope-ai-rag-eval/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentscope-ai-rag-eval"}