subagent-driven-development

Dispatch AI subagents to implement tasks and run two-stage reviews.

Updated Jan 30, 2026
One-click install
npx skills add https://github.com/ChoiHyunjin/ai_skills --skill subagent-driven-development-choihyunjin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/ChoiHyunjin/ai_skills/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/ChoiHyunjin/ai_skills --skill subagent-driven-development-choihyunjin

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the development process by breaking down implementation plans into independent tasks, each handled by a dedicated AI subagent with rigorous, multi-stage reviews.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns a fresh AI subagent for each task to ensure clean context.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for each task.
  • Use Case: Use this skill when you have a detailed feature plan and want to accelerate development by having AI agents implement and rigorously test each part of the plan sequentially within the same session.

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 automate code generation from an implementation plan using AI?

AI subagents automate code generation by breaking down an implementation plan into independent tasks, dispatching a fresh subagent for each task to ensure clean context and sequential execution within a single session.

What is the best way to run automated code review during AI-driven development?

Automated code review in AI-driven development is managed through a two-stage sequential workflow: a spec compliance review followed by a code quality review, ensuring each task meets rigorous standards before iteration.

Can I use AI subagents to handle agile development tasks sequentially?

Yes, AI subagents handle agile development tasks sequentially by decomposing a detailed feature plan into manageable units, implementing each part, and running structured multi-stage reviews within the same session.

How does task decomposition work for AI-assisted software development?

Task decomposition for AI-assisted software development works by automatically splitting a detailed implementation plan into independent tasks, with each task assigned to a dedicated AI subagent for focused execution and testing.

Do I need a detailed feature plan to start AI subagent-driven development?

Yes, you need a detailed feature plan to start AI subagent-driven development, as the structured workflow requires an implementation plan to decompose into independent tasks for sequential subagent dispatch and testing.

When should I avoid using a multi-stage AI subagent workflow for software development?

You should avoid a multi-stage AI subagent workflow if your software development task lacks a structured implementation plan, as the sequential task decomposition and two-stage review process depends on predefined independent tasks.