Update to RAG & GenAI Copilot

{
  "description": "Audit claim-level evidence support, source provenance, citation correctness, conflicting evidence and abstention behavior.",
  "included_files": [],
  "name": "audit-citations",
  "skill_md_contents": "---\nname: audit-citations\ndescription: Audit claim-level evidence support, source provenance, citation correctness, conflicting evidence and abstention behavior.\n---\n\n\n# Audit grounded answers and citations\n**Trigger:** Correct-looking answers with wrong citations, unsupported statements, citations pointing to broad pages, missing or conflicting evidence.\n\n1. Split answer into independently checkable claims; for each claim record linked source/chunk, exact supporting span, version and access scope.\n2. Mark each claim supported, contradicted, missing, stale, inaccessible, or requiring calculation/inference. Citation presence alone is not support.\n3. Check retrieval IDs → context source IDs → answer citation IDs → frontend post-processing to locate provenance mapping failures.\n4. Review whether sources conflict; apply explicit precedence/version policy or abstain and say uncertainty remains.\n5. Quantify citation precision/coverage by claim and on domain/no-answer slices; manually audit sampled cases.\n6. Propose minimal mapping and prompt changes, regression examples, and source-level authorization checks.\n\nOutput a claim/evidence matrix and prioritized remediation. Read `../../references/citations-grounding.md` and `../../references/security-boundaries.md`.\n"
}