Orchestrates large features via RFC decomposition into verifiable work units in a multi-agent DAG, with quality gates, merge queues, complexity tiers, and recovery. Use for complex, multi-pass tasks.
From muggle-ai-teamsnpx claudepluginhub multiplex-ai/muggle-ai-teams --plugin muggle-ai-teamsThis skill uses the workspace's default tool permissions.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.
Inspired by humanplane style RFC decomposition patterns and multi-unit orchestration workflows.
Use this skill when a feature is too large for a single agent pass and must be split into independently verifiable work units.
Each work unit should include:
iddepends_onscopeacceptance_testsrisk_levelrollback_planIf a unit stalls: