Update to RAG & GenAI Copilot

{
  "description": "Coordinate actual specialist agents for substantial RAG engineering tasks, with independent review and evidence handoffs.",
  "included_files": [],
  "name": "orchestrate-rag-agents",
  "skill_md_contents": "---\nname: orchestrate-rag-agents\ndescription: Coordinate actual specialist agents for substantial RAG engineering tasks, with independent review and evidence handoffs.\n---\n\n\n# RAG specialist orchestration\n**Trigger:** Substantial, separable architecture + coding + security + evaluation tasks and real subagent or orchestration tools available.\n\n1. Check available subagent tool/runtime first. A Markdown skill does **not** create live independent agents. If unavailable, perform the same checks sequentially and say so when relevant.\n2. Lead assigns narrow responsibilities: Corpus/ingestion analyst, Retrieval engineer, Evaluation engineer, Security reviewer, Implementation engineer, Operations reviewer. Choose only necessary roles.\n3. Parallelize read-only inspection or separated branches; do not allow agents to overwrite shared files or independently deploy.\n4. Freeze interface contracts, versioned corpus/eval fixture and accepted metrics before implementation.\n5. Reviewers operate independently and use actual evidence. The lead must reconcile findings, request fixes and rerun checks; never claim consensus equals validation.\n6. Require approval for production changes, elevated credentials, paid services or destructive operations. Bound time, tool calls, cost and retries.\n7. Handoff fields: scope; source files/versions; decisions; commands actually run; measured result; unresolved risks; proposed next step.\n\nRead `../../references/orchestration.md` and `../../references/evidence-contract.md`.\n"
}