skills.rest
iAMv1
iAMv1COMMUNITY
Explore all skills by this author →
WebsiteGitHub

task-decomposer

Decompose task specifications into phase-based parallel execution plans with dependency graphs.

1|1|Updated Mar 31, 2026
Search Tags:#workflow#planning#subagents#decomposition#dependency-graph#parallelism
One-click install
npx skills add https://github.com/iAMv1/agent-os --skill task-decomposer-iamv1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: task-decomposer
Source: https://github.com/iAMv1/agent-os/tree/main/skills/task-decomposer
Command: npx skills add https://github.com/iAMv1/agent-os --skill task-decomposer-iamv1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Breaks down enhanced task specifications into structured phases and parallel subagents, enabling scalable and fast task execution.

Core Features & Use Cases

  • Phase-based decomposition with explicit dependencies to prevent race conditions.
  • Automatic design of parallel subagents and handoff points for phase transitions.
  • Applies to multi-step, multi-agent workflows such as prompt-enhancement plus execution planning.

Quick Start

Provide an enhanced task specification and the skill will return a complete, parallel execution plan ready for orchestration.

Frequently Asked Questions about task-decomposer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decompose a task into a parallel execution plan?▼

Parallel execution plans are created by breaking down enhanced task specifications into structured phases and assigning independent work units to subagents. This decomposition maps explicit dependencies and defines handoff points for phase transitions.

How does phase-based decomposition prevent race conditions in multi-agent workflows?▼

Phase-based decomposition prevents race conditions by applying explicit dependency graphs and safeguards against mutable shared state between subagents. This deterministic workflow ensures independent work units execute safely without overwriting shared data.

What is the best way to map dependencies for parallel subagents?▼

Mapping dependencies for parallel subagents requires designing a deterministic workflow with defined phases and clear handoff points. This structure identifies independent work units and explicitly links their relationships to orchestrate parallel execution safely.

Do I need an enhanced task specification before generating parallel execution plans?▼

Yes, an enhanced task specification is required as the input to generate a complete parallel execution plan. Providing this detailed specification allows the workflow to automatically design subagents, map dependencies, and structure phase-based execution.

Can I use task decomposition for multi-step prompt-enhancement and execution planning?▼

Task decomposition supports multi-step, multi-agent workflows including prompt-enhancement and execution planning. It breaks these complex processes into structured phases with automatic parallel subagent assignments and safe handoff transitions.

When should I not use parallel subagents for task execution?▼

Parallel subagents should not be used when a task cannot be safely split into independent work units or when mutable shared state cannot be prevented. This approach requires clear dependency mapping and tasks that support phase-based separation.

Related Skills

Explore More Software Engineering Skills→
1molchuan1molchuan
1

oh-my-ccg-init

Verify MCP, Codex, and Gemini endpoints and initialize RPI state.

Community
Intermediate
aslaiiaslaii

gsd-execute-phase

Execute phase plans in parallel waves across subagents.

Community
Advanced
kenkenmainkenkenmain
1

sswarm

Coordinate parallel agents through a six-phase pipeline with dependency-based dispatch.

Official
Advanced
SteelMorganSteelMorgan
87

task-breakdown-linear

Generate a JSON task breakdown with dependencies and self-checks for linear execution.

Community
Intermediate