story-decomposition

Break technical specifications into small, implementable stories with dependency ordering

509 stars

Best use case

story-decomposition is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Break technical specifications into small, implementable stories with dependency ordering

Teams using story-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

$curl -o ~/.claude/skills/story-decomposition/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/maestro/skills/story-decomposition/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/story-decomposition/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How story-decomposition Compares

Feature / Agentstory-decompositionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Break technical specifications into small, implementable stories with dependency ordering

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

# Story Decomposition

## Capabilities

Breaks technical specifications into small, independently implementable stories. Establishes dependency ordering, estimates effort, and creates a dispatching queue for parallel coder execution.

## Tool Use Instructions

- Use **Read** to examine the technical specification and existing code
- Use **Grep/Glob** to find existing modules and interfaces that stories will touch
- Use **Write** to generate story definitions
- Use **Edit** to refine stories based on feedback

## Process Integration

- Used in `maestro-orchestrator.js` Phase 3 (Story Decomposition)
- Used in `maestro-development.js` (Story Prioritization)
- Maps to tasks: `maestro-architect-story-decomp`, `maestro-dev-prioritize`
- Agent: Architect
- Each story should be completable by a single coder in one batch
- Outputs feed into parallel coder dispatch

Related Skills

storybook

509
from a5c-ai/babysitter

Storybook configuration, stories, addons, interaction testing, and documentation.

storybook-docs

509
from a5c-ai/babysitter

Storybook integration for UI component documentation. Configure docs addon, generate component documentation from stories, write MDX documentation, and integrate with design systems.

user-story-generator

509
from a5c-ai/babysitter

Generate and validate user stories from various inputs including requirements, research, and feature descriptions. Apply INVEST criteria validation, create acceptance criteria, split large stories, and convert between story formats.

oral-history-interview-technique

509
from a5c-ai/babysitter

Conduct life history and testimonial interviews with appropriate prompting, active listening, and trauma-informed approaches

elearning-storyboarding

509
from a5c-ai/babysitter

Create detailed storyboards for interactive digital learning content specifying narration, visuals, interactions, and navigation

storyboard-prompting

509
from a5c-ai/babysitter

Generate detailed image prompts for storyboard frames optimized for Midjourney, DALL-E, and Stable Diffusion

data-storytelling

509
from a5c-ai/babysitter

Narrative generation skill for transforming analytical insights into compelling business stories

user-story-writer

509
from a5c-ai/babysitter

Generate and validate user stories from requirements with INVEST validation and acceptance criteria

work-unit-decomposition

509
from a5c-ai/babysitter

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

work-decomposition

509
from a5c-ai/babysitter

Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.

Task Decomposition

509
from a5c-ai/babysitter

Break epics into parallelizable tasks with acceptance criteria, effort estimates, and dependency graphs.

Story Development

509
from a5c-ai/babysitter

Implement user stories with test-driven development methodology.