Update to RAG & GenAI Copilot

{
  "description": "Diagnose wrong or missing evidence, hallucinations, stale knowledge, wrong answers, and RAG quality regressions using traces.",
  "included_files": [],
  "name": "debug-rag",
  "skill_md_contents": "---\nname: debug-rag\ndescription: Diagnose wrong or missing evidence, hallucinations, stale knowledge, wrong answers, and RAG quality regressions using traces.\n---\n\n\n# Diagnose a RAG failure\n**Trigger:** Wrong answer, missing evidence, incorrect totals, stale answer, bad citation, regression or user reports that RAG is unreliable.\n\n1. Restate the observed symptom and expected answer; collect one failing query, source truth if known, a retrieval trace and relevant version/config change.\n2. Walk layers in sequence: corpus → parse → chunks → index/freshness → ACL/filters → candidate retrieval → rerank → packed context → generation → citation/postprocess.\n3. Identify the **first proven failing layer**. Do not infer model hallucination when the evidence never reached it.\n4. State the leading hypothesis with confidence based on evidence; offer one falsifying test with expected results and safe scope.\n5. If tests/tools available, reproduce against last-known-good and a minimized fixture; record actual measurements. Otherwise label proposed commands as unrun.\n6. Propose the smallest fix, regression test, risk and rollback; separate immediate containment from permanent remediation.\n\nResponse shape for incidents: symptom → first failing boundary → evidence → decisive test → safe fix → verification and risks. Read `../../references/debugging-boundaries.md`, `../../references/incident-response.md`.\n"
}