{"id":79648,"plugin_id":"plugins_6ab42aaa4d808191be10baa770d399ad","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-04T00:11:33.826Z","digest":"83b2ff7014d3a22eac79d2c31ccd826aea4f850c52c2541f229006d7b55ce566","against":null,"payload":{"description":"Coordinate real research, art-direction, image creation and QA specialists when host execution supports subagents.","included_files":[],"name":"orchestrate-visual-specialists","skill_md_contents":"---\nname: orchestrate-visual-specialists\ndescription: Coordinate real research, art-direction, image creation and QA specialists when host execution supports subagents.\n---\n\n\n# Visual multi-agent workflows\n1. Use real subagents only if current host exposes independent execution. A skill folder or role label does not create a running worker.\n2. Route specialist work only when task requires independent, parallel investigation (e.g., research + source audit; concept exploration + brand audit). Keep routine image edits single-agent.\n3. Define per-worker scope and explicit artifact/evidence return format. Do not let two agents edit the same source artifact simultaneously.\n4. Lead agent integrates approved directions, assigns final image output to one owner, then a separate reviewer inspects it where possible.\n5. Apply budget and permission constraints. No fictitious tool use, invented agent logs, or claims that external services were contacted.\n6. Consult `../../references/orchestration.md`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}