work-unit-decomposition

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

509 stars

Best use case

work-unit-decomposition is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

Teams using work-unit-decomposition should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/work-unit-decomposition/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/metaswarm/skills/work-unit-decomposition/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/work-unit-decomposition/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How work-unit-decomposition Compares

Feature / Agentwork-unit-decompositionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Work Unit Decomposition

## Overview

Break implementation plans into discrete, testable work units. Each unit has enumerated Definition of Done items, declared file scope, dependency mapping, and optional human checkpoint flags.

## When to Use

- After plan review gate approval
- When decomposing a large feature into implementable chunks
- When preparing for orchestrated execution

## Work Unit Structure

Each work unit specifies:
- **ID** - Unique identifier
- **Title** - Human-readable description
- **Definition of Done** - Enumerated checklist items
- **File Scope** - Which files the unit may modify
- **Dependencies** - Other work units this depends on
- **Human Checkpoint** - Whether human approval is needed before execution
- **Parallel Safe** - Whether it can execute alongside other units

## Human Checkpoint Triggers

Mark human checkpoints for:
- Schema or database changes
- Security-sensitive code paths
- New architectural patterns not seen in codebase
- External API integrations
- Breaking changes to public interfaces

## Agents Used

- `agents/architect/` - Creates the decomposition
- `agents/cto/` - Validates TDD readiness per unit

## Tool Use

Invoke as part of: `methodologies/metaswarm/metaswarm-orchestrator` (Phase 4)

Related Skills

pnpm-workspaces

509
from a5c-ai/babysitter

pnpm workspace patterns and dependency management.

Network Protocol Analysis Skill

509
from a5c-ai/babysitter

Network protocol capture, analysis, and fuzzing capabilities

contract-test-framework

509
from a5c-ai/babysitter

Consumer-driven contract testing for SDK-API compatibility. Generate Pact consumer tests, verify provider contracts, configure Pact broker, and implement can-i-deploy checks.

cli-framework-builder

509
from a5c-ai/babysitter

Build command-line interfaces for SDK interaction

network-performance

509
from a5c-ai/babysitter

Expert skill for network performance analysis and optimization. Analyze packet captures, identify network latency bottlenecks, configure TCP tuning parameters, analyze connection pooling behavior, debug TLS handshake performance, and optimize HTTP/2 and HTTP/3 settings.

network-testing

509
from a5c-ai/babysitter

Comprehensive network testing, benchmarking, and performance validation skill

network-simulation

509
from a5c-ai/babysitter

Skill for network condition simulation, emulation, and chaos engineering

Mobile Testing Frameworks

509
from a5c-ai/babysitter

Comprehensive mobile testing framework expertise

unreal-networking

509
from a5c-ai/babysitter

Unreal Engine networking skill for replication, RPCs, relevancy, and dedicated server architecture.

unreal-gamesframework

509
from a5c-ai/babysitter

Unreal Engine Gameplay Ability System (GAS) skill for attributes, abilities, and gameplay effects.

unity-vfx-graph

509
from a5c-ai/babysitter

Unity Visual Effect Graph skill for GPU particle systems, procedural effects, and high-performance visual effects.

unity-urp

509
from a5c-ai/babysitter

Universal Render Pipeline configuration skill for Unity, including custom shaders, lighting setup, post-processing effects, and render feature development.