Goal Decomposer for Openclaw

A powerful utility that translates high-level natural language intentions into hierarchical, structured, and prioritized task lists.

johnnie23919
v1.0.0
Apr 26, 2026
0
374
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install goal-decomposer

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install goal-decomposer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Goal Decomposer?

The Goal Decomposer is a sophisticated tool within the ecosystem of Openclaw Skills designed to bridge the gap between abstract human intentions and actionable machine steps. It takes natural language descriptions and automatically refines them into a structured task tree, ensuring that every part of a complex goal is accounted for and manageable.

By strictly adhering to the MECE (Mutually Exclusive, Collectively Exhaustive) principle, this skill ensures that tasks do not overlap and that no critical steps are missed. It organizes objectives into a clear hierarchy, usually limited to three levels of depth, and assigns clear priorities (P0, P1, P2) to help Openclaw Skills prioritize the most critical operations first.

Goal Decomposer Use Cases

  • Breaking down vague project requests like product research into specific, actionable sub-steps.
  • Generating hierarchical task trees for complex multi-stage coding projects.
  • Structuring workflows for autonomous AI agents where execution order and dependencies are critical.
  • Clarifying the scope of work for team projects by defining high-level goals and sub-tasks.

How Goal Decomposer Works

  1. The skill receives a natural language goal along with optional context and constraints.
  2. It analyzes the input to identify the core components required to achieve the objective.
  3. It applies MECE principles to create a non-overlapping and complete set of sub-tasks.
  4. The system assigns unique IDs and priority levels to each task and identifies logical dependencies.
  5. It produces a structured JSON output that defines the root goal, the hierarchy of tasks, and the recommended execution sequence.

Goal Decomposer Setup

To begin using this skill within your project, ensure it is installed and available in your environment:

# Install the goal-decomposer package
openclaw install goal-decomposer

# The core decomposition logic is located in the scripts directory
python scripts/decompose.py

Goal Decomposer Data Schema & Taxonomy

Key Description
root_goal The original high-level goal input provided by the user.
tasks A list of task objects including ID, title, priority, and sub-tasks (children).
priority Priority levels ranging from P0 (highest) to P2.
spawn_hint Suggestions for how sub-tasks should be handled by the agent.
execution_order A list of task IDs representing the logical order of operations.

Goal Decomposer Advanced Features

  • RESOLVER Integration: Automatically route generated sub-tasks to the most relevant Openclaw Skills based on task type.
  • Autonomous Spawning: Support for sessions_spawn to allow sub-tasks to be executed by independent agent sessions.
  • Dependency Mapping: Advanced logic to identify and label depends_on fields for complex project management.
  • MECE Validation: A built-in check to ensure task lists are logically sound and comprehensive.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*