beads

Decompose implementation plans into atomic tasks with dependencies and references.

Updated Jun 12, 2025
One-click install
npx skills add https://github.com/quitgenius/ai-engineering --skill beads-quitgenius
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: beads
Source: https://github.com/quitgenius/ai-engineering/tree/main/claude-skills/beads
Command: npx skills add https://github.com/quitgenius/ai-engineering --skill beads-quitgenius

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill breaks down complex project specifications and implementation plans into small, manageable, and independently verifiable tasks optimized for AI agent workflows, ensuring efficient and structured development.

Core Features & Use Cases

  • Task Decomposition: Converts high-level specs and implementation plans into atomic "beads" (tasks).
  • AI Workflow Optimization: Creates tasks sized for AI context windows, with clear goals and verification steps.
  • Dependency Management: Establishes task dependencies for logical execution order.
  • Use Case: After creating an implementation plan for a new feature, use this Skill to automatically generate a series of small, actionable tasks for the AI to implement, each with defined success criteria and references to existing code patterns.

Quick Start

Use the beads skill to decompose the implementation plan for ticket PAN-123 into atomic tasks.

Frequently Asked Questions about beads

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decompose project specifications into AI-optimized tasks?

Task decomposition for AI workflows converts high-level specs into atomic, verifiable units of work. It creates small tasks sized for AI context windows with clear goals, defined dependencies, and references to existing code patterns and architecture decision records.

How do I break down an implementation plan into smaller verifiable units?

Breaking down an implementation plan involves processing it through the beads issue tracker to generate small, actionable tasks. Each resulting task receives defined success criteria and references to existing code patterns, ensuring alignment with project scope and architectural decisions.

Can I manage task dependencies and execution order for AI agent workflows?

Yes, managing task dependencies for AI agent workflows is supported during decomposition. The system establishes dependencies between atomic tasks to enforce a logical execution order, ensuring independently verifiable units of work follow architectural requirements.

Does this task decomposition approach work with existing architecture decision records?

Yes, task decomposition works with existing architecture decision records. The generated atomic tasks include explicit references to ADRs and existing code patterns, managing the task lifecycle from creation to completion while ensuring alignment with architectural decisions.

What is the best way to track the lifecycle of AI development tasks?

Tracking the lifecycle of AI development tasks is best handled by an issue tracker managing them from creation to completion. This ensures each atomic unit of work remains aligned with project scope and architectural decisions throughout the structured development process.

When should I avoid atomic task decomposition for my implementation plan?

You should avoid atomic task decomposition when your implementation plan already lacks defined architectural decisions. The process relies on creating small, verifiable units with dependencies and references to ADRs, making it less suited for simple or undefined project scopes.