task-decomposer

Break vague natural-language problems into DAG-ready sub-task definitions with dependencies.

Updated Mar 27, 2026
One-click install
npx skills add https://github.com/CenredJun/openclaw-claudecode-setup-kit --skill task-decomposer-cenredjun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-decomposer
Source: https://github.com/CenredJun/openclaw-claudecode-setup-kit/tree/main/skills/task-decomposer
Command: npx skills add https://github.com/CenredJun/openclaw-claudecode-setup-kit --skill task-decomposer-cenredjun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Breaks vague natural-language problems into concrete sub-task definitions that can be scheduled in a directed acyclic graph (DAG). It identifies phases, dependencies, and parallelization opportunities, and highlights vague/pluripotent nodes for future refinement.

Core Features & Use Cases

  • Domain detection to select and load the appropriate meta-skill for decomposition
  • Phase-aware planning to generate concrete and vague sub-tasks with dependency information
  • Output-ready decomposition that can drive DAG planners, schedulers, and sub-agent mapping

Quick Start

Provide a problem description and request a structured DAG-ready decomposition with phases, tasks, and dependencies.

Frequently Asked Questions about task-decomposer

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

FAQPage Schema
How do I break down a vague problem description into sub-tasks for a DAG scheduler?

You provide a natural-language problem description and the task-decomposer outputs concrete sub-task definitions structured with phases, dependencies, and parallelization opportunities ready for DAG scheduling.

What is task decomposition with directed acyclic graph dependencies?

Task decomposition with DAG dependencies involves breaking a problem into phases and sub-tasks, identifying execution dependencies, and mapping parallelization opportunities so downstream DAG schedulers can execute nodes efficiently.

Can I identify parallelization opportunities when planning task phases?

Yes, phase-aware planning identifies parallelization opportunities by analyzing dependencies between generated sub-tasks, allowing downstream DAG planners to map independent nodes for concurrent execution.

Does the decomposition handle vague sub-tasks or only fully defined requirements?

The decomposition handles both by generating concrete sub-task definitions while explicitly flagging vague or pluripotent nodes for future refinement rather than forcing premature specification.

Do I need a specific domain framework to generate task dependencies?

No specific framework is required; the Skill applies domain meta-skills to detect the problem domain automatically and generates structured sub-task dependencies tailored to that specific domain.