Engineering
task-breakdown avatar

task-breakdown

Break down complex development requests into sequenced, actionable tasks for multi-agent delegation in Claude Code environments.

Introduction

The task-breakdown skill is an architectural orchestration tool designed for multi-agent development frameworks like Claude Code. It allows developers to decompose high-level feature requests, refactoring needs, or complex system integrations into discrete, logical tasks that can be mapped to specialized agents. By following a structured process—identifying scope, listing required components (Database, Backend, Frontend, iOS, DevOps, Designer), determining dependencies, and assessing technical complexity—this skill ensures that large-scale development projects are executed in the correct sequence. It is particularly effective for full-stack, cross-platform, and API-heavy projects where architectural consistency is critical.

  • Automatically maps user requirements to specialized agents such as Database (schema/migrations), Backend (API/logic), Frontend (React/Next.js), iOS (SwiftUI), Designer (branding/themes), and DevOps (CI/CD/Docker).

  • Provides standardized patterns for complex flows, including Web, iOS, and full cross-platform application architectures.

  • Enforces strict sequencing rules, such as Database-before-Backend, Backend-before-Frontend, and Designer-before-Frontend, preventing common integration pitfalls.

  • Facilitates the creation of actionable task templates including task IDs, complexity levels (Simple, Medium, Complex), platform targets, and explicit dependency tracking.

  • Supports the 'Hub Architecture' by generating delegation requests that the main conversation thread can execute sequentially or in parallel.

  • Input: High-level natural language development requests (e.g., 'Build a social media app with web and iOS').

  • Output: A comprehensive, ordered list of tasks categorized by agent, platform, and execution dependency.

  • Best for: Architecting new features, managing complex refactoring, and orchestrating work across multiple specialized AI agents.

  • Constraint: Designed specifically for systems where subagents cannot spawn other agents directly, requiring a Hub to process the breakdown. Follow the sequencing rules provided to ensure reliable agent interaction.

Repository Stats

Stars
13
Forks
4
Open Issues
0
Language
Python
Default Branch
main
Sync Status
Idle
Last Synced
May 3, 2026, 06:07 PM
View on GitHub