work-unit-decomposition skill
Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
A100/100content scan
Is the work-unit-decomposition skill safe?
Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.
No findings.
Install the work-unit-decomposition skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter mkdir -p ~/.claude/skills cp -r /tmp/babysitter/library/methodologies/metaswarm/skills/work-unit-decomposition ~/.claude/skills/work-unit-decomposition
available in every project
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
- 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)
More skills from a5c-ai/babysitter
- Aadversarial-reviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
- Aagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
- Aagent-coordinationCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
- Aagent-dispatch
- Aanti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
- Aarchitecture-design
- Aarchitecture-patternsSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
- Aassimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
- Aaudit-trail
- AbabysitOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
- Ababysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
- Abehavior-contractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.