{"id":79578,"plugin_id":"plugins_6ab427b8c6908191a438adb4b6f315d4","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-04T00:11:26.256Z","digest":"e916fbf5d922206469d0f2cce507b7a9473c2451160b7028d9be5683042a5967","against":null,"payload":{"description":"Coordinate independent Unix command reviewers or platform specialists only when genuine subagents are supported.","included_files":[],"name":"orchestrate-specialists","skill_md_contents":"---\nname: orchestrate-specialists\ndescription: Coordinate independent Unix command reviewers or platform specialists only when genuine subagents are supported.\n---\n\n# Specialist orchestration for complex shell tasks\n\n## Scope and execution truth\nThis is a skills-only assistant workflow. Do not claim to execute system commands, inspect the user's host, install packages, or complete side effects without actual authorized tools and observed results. User-pasted output is evidence, not a machine connection.\n\n## Procedure\n1. Check for actual host-supported subagent invocation; this skill alone does not create agents or a tool backend.\n2. For complex independent tasks, assign a portability reviewer, safety reviewer and implementation/debug reviewer with narrow nonoverlapping scopes.\n3. Avoid running multiple workers that modify the same files; reviewers should not execute risky commands and should return evidence-backed findings.\n4. Require each specialist report tool access, commands actually executed, tests, uncertainty and change scope. No fabricated parallel work.\n5. Lead agent reconciles disagreements, chooses the smallest verified solution, and maintains one user-visible decision record.\n6. For small tasks or without true subagents, do the checks sequentially without implying parallel execution.\n\n## Relevant references\n- Read `../../references/orchestration-and-evidence.md` for domain-specific guidance.\n- Read `../../references/safety-risk-model.md` for domain-specific guidance.\n- Read `../../references/source-registry.md` for domain-specific guidance.\n\n## Completion checks\n- No simulated agents\n- No simultaneous conflicting writes\n- Single truthful final report\n\n## Deliverable\nUse the minimum format that makes the answer actionable: the actual command or patch, platform assumptions, a preview before risky changes, and a reproducible validation step. Clearly label proposed actions versus observed execution.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}