{"id":77675,"plugin_id":"plugins_6ae8d0ba8e808191a5a7ac9a01d005f8","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-03T00:15:29.423Z","digest":"99e8ad187b16d5926d5e1f116c3b7a83d34a25015b9cf9814f032855b2c99ae9","against":null,"payload":{"description":"Coordinate real specialist agents for a complex game project while maintaining single-agent fallback and independent verification.","included_files":[],"name":"orchestrate-game-agents","skill_md_contents":"---\nname: orchestrate-game-agents\ndescription: Coordinate real specialist agents for a complex game project while maintaining single-agent fallback and independent verification.\n---\n\n# Orchestrate Game Agents\n\n\n1. Read `../../references/orchestration.md`. A role description is not an independent agent; check whether real subagent tools or an authorized backend are available.\n2. Lead Game Director owns project scope, game-design brief, engine choice, task graph, user approvals and integration.\n3. Delegate independent subproblems only when helpful: Game Designer, Engine Architect, Art Director, Gameplay Developer, Level Designer, Audio, QA/Playtester and Release. Use few agents for small games.\n4. Freeze interfaces and shared asset naming before parallel implementation. Give separate non-overlapping files/branches/worktrees and concrete acceptance checks.\n5. Keep security and QA review read-only and independent of implementers. Reconcile cross-agent decisions centrally; never claim '8 agents completed' based on simulated personas.\n6. Limit token/time/cost budgets and external side effects. Report actual subagent tasks, commands, artifacts and failures, with sequential fallback identified when used.\n\n## Execution truth and safeguards\n- A skill is an instruction workflow, not a remotely running game engine or a separately running AI agent. Inspect tools and repo state before claiming execution.\n- Preserve existing projects, names, dependencies, save formats, and user work unless a change is explicitly requested. Obtain approval for deployment, payments, destructive edits, publication, and major third-party connections.\n- Avoid reproducing protected commercial characters, levels, dialogue, soundtracks, logos, or copyrighted assets unless authorized. For assets, record origin and license. Read `../../references/security-and-rights.md`.\n- Report what was implemented, what was actually run, what failed, and what remains unverified; never describe proposed tests as passed.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}