work-decomposition
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
Best use case
work-decomposition is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
Teams using work-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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/work-decomposition/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How work-decomposition Compares
| Feature / Agent | work-decomposition | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.
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 Decomposition ## Overview Break high-level goals into MEOWs (Molecular Expressions of Work) - the fundamental atomic units in Gas Town. Each MEOW becomes a bead (git-backed work unit) or wisp (ephemeral task). ## When to Use - Before creating a convoy - When a goal is too large for a single agent - When parallel execution would benefit progress - When work needs tracked attribution ## Process 1. **Analyze** the goal and project context 2. **Identify** natural seams for decomposition 3. **Create MEOWs** with clear boundaries and dependencies 4. **Classify** as beads (persistent) or wisps (ephemeral) 5. **Map dependencies** between MEOWs 6. **Estimate** effort and assign priorities ## Decomposition Principles - Each MEOW should be completable by a single agent - Dependencies should form a DAG (no cycles) - Prefer more smaller beads over fewer larger ones - Wisps for throwaway work (scaffolding, exploration) - Every MEOW gets attribution tracking ## Tool Use Invoke via babysitter process: `methodologies/gastown/gastown-orchestrator` (analyze-work step)
Related Skills
pnpm-workspaces
pnpm workspace patterns and dependency management.
Network Protocol Analysis Skill
Network protocol capture, analysis, and fuzzing capabilities
contract-test-framework
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
Build command-line interfaces for SDK interaction
network-performance
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
Comprehensive network testing, benchmarking, and performance validation skill
network-simulation
Skill for network condition simulation, emulation, and chaos engineering
Mobile Testing Frameworks
Comprehensive mobile testing framework expertise
unreal-networking
Unreal Engine networking skill for replication, RPCs, relevancy, and dedicated server architecture.
unreal-gamesframework
Unreal Engine Gameplay Ability System (GAS) skill for attributes, abilities, and gameplay effects.
steamworks-networking
Steam P2P networking skill for lobbies and relay servers.
p2p-networking
Peer-to-peer networking skill for NAT punch-through and relay servers.