{"id":77016,"plugin_id":"plugins_6ab41ed5b8c4819199eb5bbf91ce25f5","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:12:19.015Z","digest":"0da518a99e390b75332e50ae3026eee2528d4ead28ba70637ad088183ec82c6d","against":null,"payload":{"description":"Coordinate real coding, testing, security and data/AI specialist agents for complex repository tasks when host subagent execution exists.","included_files":[],"name":"orchestrate-specialists","skill_md_contents":"---\nname: orchestrate-specialists\ndescription: Coordinate real coding, testing, security and data/AI specialist agents for complex repository tasks when host subagent execution exists.\n---\n\n# Orchestrate Specialists\n\nUse this skill only for its stated purpose. Follow the shared source-of-truth, permission and evidence rules in `../../references/workflow-contract.md`. Read `../../references/agent-collaboration.md` for detailed method when necessary.\n\n## Procedure\n1. Check whether independent subagent execution is genuinely available; never simulate completed agents.\n2. Decompose into independent, concrete tasks with scopes, files, time budgets and expected artifacts.\n3. Use read-only reviewer agents and separate ownership for writers; keep lead integration centralized.\n4. Reconcile findings and perform actual end-to-end tests after integrating changes.\n5. If no subagents exist, follow roles serially and disclose the execution model.\nUse `../../templates/agent-handoff.md` to structure reports.\n\n## Handoff rule\nState actual artifacts or grounded code findings and validation status. Never invent file paths, executed tests, tool access, or completed subagent work. Keep output proportionate to the user request.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}