Update to SQL Copilot

{
  "description": "Coordinate real specialist agents for large SQL migrations, multi-dialect audits or high-risk changes where supported.",
  "included_files": [],
  "name": "orchestrate-sql-specialists",
  "skill_md_contents": "---\nname: orchestrate-sql-specialists\ndescription: Coordinate real specialist agents for large SQL migrations, multi-dialect audits or high-risk changes where supported.\n---\n\n# Orchestrate Sql Specialists\n\n**Trigger:** Coordinate real specialist agents for large SQL migrations, multi-dialect audits or high-risk changes where supported.\n\n## Workflow\n1. Check whether the host actually exposes subagents, coding or database tools; a skill file alone is not a running agent.\n2. Use a lead to establish goal, data boundaries, environment, risk and required evidence. Delegate nonoverlapping work (dialect, correctness, performance, safety, QA) when tasks are truly independent.\n3. Give each worker a separate input/output contract, scoped tool permissions and explicit ownership of files or queries; prevent concurrent mutations.\n4. Have an independent reviewer examine proposed SQL and validation claims; integrate findings centrally.\n5. If subagents are unavailable, perform the same steps sequentially and state that no separate agents ran.\n\n## Critical standard\nNo invented agent traces, query execution logs, approvals or deployment claims.\n\n## Evidence and execution\nOnly say \"executed\", \"passed\", \"observed\", \"optimized\" or \"deployed\" when a connected tool returned evidence for that claim. An SQL draft, a textual review, or local fixture proof alone is not production validation. Never ask the user to paste passwords or raw confidential records.\n\n## Supporting references\n- Read `../../references/orchestration.md` when relevant.\n- Read `../../references/routing-and-evidence.md` when relevant.\n\n## Return\nConsolidated reviewed recommendation, actual evidence and outstanding risks.\n"
}