subagent-driven-development

Dispatch AI subagents to execute implementation tasks with two-stage reviews.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/raduceuca/wcgw-fun --skill subagent-driven-development-raduceuca
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/raduceuca/wcgw-fun/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/raduceuca/wcgw-fun --skill subagent-driven-development-raduceuca

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines complex development tasks by breaking them down into manageable steps, each handled by a dedicated AI subagent with rigorous review processes, ensuring high-quality code and efficient iteration.

Core Features & Use Cases

  • Task Decomposition: Breaks down implementation plans into independent tasks.
  • Subagent Dispatch: Assigns a fresh AI subagent for each task.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for every task.
  • Use Case: When you have a detailed feature plan with multiple distinct coding tasks, this Skill ensures each task is implemented correctly, reviewed thoroughly, and integrated seamlessly, accelerating the development cycle without sacrificing quality.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./plans/new-feature.md.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I execute an implementation plan using AI subagents?

You can execute an implementation plan by dispatching independent AI subagents for each task, ensuring rapid iteration and context preservation within a single development session.

What is subagent-driven development and how does it work?

Subagent-driven development is a process that breaks down implementation plans into independent tasks, assigning a fresh AI subagent to execute each task with rigorous review processes.

How does the two-stage review process ensure code quality?

The two-stage review process ensures code quality by first checking spec compliance for every task, followed immediately by a dedicated code quality review before integration.

Can I use subagent-driven development for complex feature plans with multiple coding tasks?

Yes, subagent-driven development is designed for complex feature plans with multiple distinct coding tasks, ensuring each task is implemented correctly and integrated seamlessly without sacrificing quality.

Do I need a detailed feature plan to use AI agents for task execution?

Yes, you need a detailed feature plan located in a file, such as a markdown document, which the subagents use to decompose work into manageable steps for execution.

What are the limitations of using independent AI subagents for task execution?

A limitation of using independent AI subagents is that task execution is managed within a single session, meaning context preservation is bounded by that session's constraints and rapid iteration capacity.