work-decomposition
SkillAI & modelsOnce added, your AI can take a big goal and break it down into small, trackable units of work it handles one by one. Each unit is a MEOW (Molecular Expression of Work), a single atomic piece based on a bead-based work model. This makes large goals easier to start and easier to follow along with.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then give your AI a goal that feels too big to handle in one go. It will break the goal into small units of work and start following them one by one.
Then ask your AI: use the work-decomposition skill
What your AI can do with it
- Split a large goal into small, separate units of work
- Create MEOWs, small atomic pieces of work that can be tracked
- Work through the pieces one at a time
- Keep track of each unit as the work moves forward
- Structure work using a bead-based model, where each bead is one small trackable piece
What this skill tells your AI
The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/gastown/skills/work-decomposition/SKILL.md and read by ahel’s review.
- When a goal is too large for a single agent
- When parallel execution would benefit progress
- When work needs tracked attribution
Process
- Analyze the goal and project context
- Identify natural seams for decomposition
- Create MEOWs with clear boundaries and dependencies
- Classify as beads (persistent) or wisps (ephemeral)
- Map dependencies between MEOWs
- 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)
Signals
- GitHub stars
- 2k
- Forks
- 106
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
work-decomposition- Source
- github.com/a5c-ai/babysitter