Stats
Actions
Tags
From design-agent-orchestration
Decomposes complex user goals into subtasks for multi-agent systems using sequential, parallel, hierarchical, conditional, and iterative strategies. Covers granularity, ambiguity handling, and design artifacts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/design-agent-orchestration:task-decompositionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Users come with goals, not subtasks. Task decomposition is how a multi-agent system breaks a complex user goal into pieces that individual agents can handle — and then reassembles the results into something coherent.
Users come with goals, not subtasks. Task decomposition is how a multi-agent system breaks a complex user goal into pieces that individual agents can handle — and then reassembles the results into something coherent.
For each type of user goal the system handles:
How finely to decompose matters:
User goals are often ambiguous. The system needs to:
npx claudepluginhub owl-listener/ai-design-skills --plugin design-agent-orchestrationDecompose complex tasks into parallel units, design dependency graphs with blockedBy/blocks, and write effective task descriptions with acceptance criteria.
Breaks down implementation plans into detailed task lists with agent contexts, acceptance criteria, dependencies, priorities, complexity levels, and status tracking.
Decomposes contextualized plans into atomic, independently executable tasks with embedded context, CLEAR ordering, CoVe checks, and dependency graphs for parallel execution.