Update to Data Engineering Copilot

{
  "description": "Coordinate actual specialist agents for complex data engineering tasks only when supported execution tools exist.",
  "included_files": [],
  "name": "orchestrate-data-agents",
  "skill_md_contents": "---\nname: orchestrate-data-agents\ndescription: Coordinate actual specialist agents for complex data engineering tasks only when supported execution tools exist.\n---\n\n\n# Data engineering multi-agent coordination\n**Trigger:** Work naturally separates into architecture, implementation, validation/security and independent QA on a substantial task.\n\n1. Check that the current host actually provides subagents or an authorized backend. Markdown role descriptions are **not** independent agents. If unavailable, perform phases sequentially with truthful attribution.\n2. Lead sets scope, data access, acceptance tests, costs, privileges and approvals. Typical specialists: architect, pipeline implementer, quality verifier, operational/security reviewer.\n3. Parallelize read-only discovery and independent critique when possible. Assign exclusive files/worktrees for write tasks; never let multiple agents mutate the same live data.\n4. Require each agent to report evidence, commands actually run, files changed, assumptions, security issues, blocker and test status.\n5. Have QA/security independently review implemented artifacts; do not treat two agreeing agents as proof of correctness.\n6. Integrate changes centrally, rerun test suite and retain one final audit trail. Never start production jobs or deploy without permission.\n\nRead `../../references/agent-orchestration.md` and `../../templates/agent-handoff.md`.\n"
}