Task Decomposition
SkillProductivityLets your agent turn a technical plan into ordered development tasks with dependencies, effort estimates, and parallelization hints.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Task Decomposition skill
About this capability
Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.
What this skill tells your AI
The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/ccpm/skills/task-decomposition/SKILL.md and read by ahel’s review.
Break epics into parallelizable tasks with acceptance criteria, effort estimates, and dependency graphs.
Agent
Task Analyst - task-analyst
Workflow
- Analyze epic and identify 4-5 parallel work streams
- Decompose each stream into concrete tasks (parallel)
- Set acceptance criteria in Given/When/Then format
- Estimate effort (S/M/L/XL) and set parallelization flags
- Build cross-stream dependency graph
- Validate coverage against PRD user stories
- Fill gaps with additional tasks if needed
- Write task files to .claude/epics//.md
Inputs
projectName- Project namefeatureName- Feature identifierepic- Epic from Phase 2prd- PRD from Phase 1parallelAgents- Max parallel agents (default: 5)
Outputs
- Task list with acceptance criteria and effort estimates
- Work stream definitions
- Dependency graph with execution waves
- Coverage report with PRD traceability
Process Files
ccpm-task-decomposition.js- Standalone decompositionccpm-orchestrator.js- Phase 3 of full lifecycle
Signals
- GitHub stars
- 2k
- Forks
- 106
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
task-decomposition- Source
- github.com/a5c-ai/babysitter