subagent-driven-development

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

1|Updated Dec 15, 2025
One-click install
npx skills add https://github.com/mihaamiharu/twe --skill subagent-driven-development-mihaamiharu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/mihaamiharu/twe/tree/main/.agent/skills/subagent-driven-development
Command: npx skills add https://github.com/mihaamiharu/twe --skill subagent-driven-development-mihaamiharu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the implementation of complex plans by breaking them down into independent tasks, each handled by a dedicated AI subagent with rigorous, multi-stage review processes.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a larger implementation plan into manageable, discrete tasks.
  • Subagent Dispatch: Assigns each task to a fresh AI subagent for focused implementation.
  • Two-Stage Review: Enforces a spec compliance review followed by a code quality review for every task.
  • Iterative Refinement: Manages feedback loops where subagents fix issues identified during reviews.
  • Use Case: Implementing a new software feature involves multiple steps like setting up a database schema, building a UI component, and writing API endpoints. This Skill ensures each step is completed correctly and to high standards before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at 'docs/plans/feature-plan.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 agents for iterative development?

Iterative development with AI agents executes implementation plans by dispatching independent subagents for each task. It manages a two-stage review process for spec compliance and code quality, facilitating rapid iteration within a single session.

What is the two-stage code review process for AI agent task implementation?

The two-stage code review process enforces spec compliance first, then code quality for every task. This ensures each implementation step meets high standards before moving to the next.

How do I manage task decomposition for complex software features?

Task decomposition for complex software features breaks down a larger implementation plan into manageable, discrete tasks. Each task is assigned to a fresh AI subagent for focused implementation.

Can I integrate subagent-driven development with planning and branch finishing skills?

Yes, subagent-driven development integrates with planning, code review, and branch finishing skills. This allows you to execute implementation plans located at specific file paths like 'docs/plans/feature-plan.md'.

What are the limitations of using AI subagents for iterative development?

The limitations of using AI subagents for iterative development include the need for a pre-existing implementation plan. The skill focuses on execution and review, not initial planning.