ReddRadar
Agent skill
task-decomposition
Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.
Install this agent skill to your Project
npx add-skill https://github.com/a5c-ai/babysitter/tree/main/library/methodologies/spec-kit/skills/task-decomposition
SKILL.md
Task Decomposition
Overview
Decompose a technical plan into actionable development tasks. Each task is atomic, has clear acceptance criteria traceable to specification requirements, and includes dependency information for optimal execution ordering.
When to Use
- After technical plan is approved, before implementation
- When breaking down a large feature into implementable units
- When identifying parallelization opportunities in a task set
- When estimating effort and critical path for a feature
Key Principle
Every task must trace back to at least one specification requirement. Tasks must be atomic enough for a single development session. Dependency graphs must be acyclic.
Process
- Decompose components - Break architecture components into implementable tasks
- Define tasks - Each with id, title, description, acceptance criteria, dependencies, effort
- Build dependency graph - Show task ordering constraints
- Identify parallel groups - Tasks with no mutual dependencies
- Determine critical path - Longest dependency chain
- Generate test tasks - Testing tasks alongside implementation
- Map to requirements - Traceability from tasks to specification
- Human review - Approve task list before implementation
Tool Use
Invoke via babysitter process: methodologies/spec-kit/spec-kit-planning (task decomposition phase)
Full pipeline: methodologies/spec-kit/spec-kit-orchestrator
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
a5c-ai/babysitter
gsd-tools
Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).
a5c-ai/babysitter
model-profile-resolution
Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.
a5c-ai/babysitter
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
a5c-ai/babysitter
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
a5c-ai/babysitter
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
a5c-ai/babysitter
frontmatter-parsing
YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.
Didn't find tool you were looking for?