d-o-hub

task-decomposition

4
0
# Install this skill:
npx skills add d-o-hub/rust-self-learning-memory --skill "task-decomposition"

Install specific skill from multi-skill repository

# Description

Break down complex tasks into atomic, actionable goals with clear dependencies and success criteria. Use when planning multi-step projects, coordinating agents, or decomposing complex requests.

# SKILL.md


name: task-decomposition
description: Break down complex tasks into atomic, actionable goals with clear dependencies and success criteria. Use when planning multi-step projects, coordinating agents, or decomposing complex requests.


Task Decomposition

Break down complex tasks into atomic, actionable goals with clear dependencies.

When to Use

  • Complex user requests with multiple components
  • Multi-phase projects requiring coordination
  • Tasks that could benefit from parallel execution
  • Planning agent coordination strategies

Decomposition Framework

1. Requirements Analysis

  • Primary objective
  • Implicit requirements (quality, performance)
  • Constraints (time, resources)
  • Success criteria

2. Goal Hierarchy

Main Goal
β”œβ”€ Sub-goal 1
β”‚  β”œβ”€ Task 1.1 (atomic)
β”‚  └─ Task 1.2 (atomic)
β”œβ”€ Sub-goal 2
└─ Sub-goal 3

3. Dependency Types

Type Symbol Example
Sequential A β†’ B β†’ C B needs A's output
Parallel A─┐ B─┐ Cβ”€β”˜ Independent, concurrent
Converging A─┐ B─┼─> D D needs A, B, C
Resource A, B Sequential or pooled

4. Success Criteria

For each task:
- Input: What data/state is needed
- Output: What artifacts will be produced
- Quality: Performance, testing, docs requirements

Decomposition Patterns

Pattern Use Case
Layer-Based Architectural changes (data, logic, API, test, docs)
Feature-Based New features (MVP, error handling, optimization, integration)
Phase-Based Large projects (research, foundation, core, integration, polish)
Problem-Solution Debugging (reproduce, diagnose, design, fix, verify, prevent)

Quality Checklist

βœ“ Atomic and actionable
βœ“ Dependencies clearly identified
βœ“ Success criteria measurable
βœ“ No task too large (>4 hours)
βœ“ Parallelization opportunities identified

βœ— Tasks too large or vague
βœ— Missing dependencies
βœ— Unclear success criteria
βœ— Missing quality/testing tasks

Integration with GOAP

Task decomposition is Phase 1 of GOAP:
1. Receive request
2. Apply decomposition
3. Create execution plan
4. Execute with monitoring
5. Report results

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.