subagent-driven-development

Automates implementation plans by dispatching AI subagents and running two-stage reviews.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/novvoo/skill-router --skill subagent-driven-development-novvoo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/novvoo/skill-router/tree/main/agent/skills/subagent-driven-development
Command: npx skills add https://github.com/novvoo/skill-router --skill subagent-driven-development-novvoo

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of implementing development plans by breaking them down into independent tasks, each handled by a dedicated AI subagent with rigorous review stages, ensuring high-quality code and rapid iteration.

Core Features & Use Cases

  • Task Decomposition: Breaks down complex plans into manageable, independent tasks.
  • Subagent Dispatch: Assigns each task to a specialized "implementer" subagent.
  • Two-Stage Review: Enforces spec compliance and code quality checks after each task.
  • Iterative Improvement: Manages feedback loops for fixing issues identified during reviews.
  • Use Case: Implementing a new feature from a detailed plan, where each part of the feature can be developed and reviewed independently, leading to faster delivery without sacrificing quality.

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 automate code generation from a development plan?

You can automate code generation from a development plan by dispatching independent AI subagents for each decomposed task. The process includes rigorous two-stage reviews for spec compliance and code quality, managing iterative fixes to ensure high-quality development cycles within a single session.

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

Subagent-driven development automates executing plans by assigning each decomposed task to a specialized AI implementer subagent. It enforces spec compliance and code quality through two-stage reviews, managing iterative feedback loops to fix issues and ensure rapid, high-quality development cycles.

How do I ensure code quality when using AI agents for software development?

Ensuring code quality with AI agents requires a rigorous two-stage review process after each task implementation. This enforces spec compliance and code quality checks, managing iterative feedback loops to fix issues identified during reviews for high-quality development.

Can I implement a complex feature plan faster by breaking it into independent tasks?

Breaking down a complex feature plan into manageable, independent tasks assigned to dedicated AI subagents enables faster delivery. Each part is developed and reviewed independently with rigorous two-stage reviews, ensuring rapid iteration without sacrificing quality.

Do I need a detailed plan file to use automated AI agents for code review and generation?

A detailed implementation plan file is required to use automated AI subagents for code generation and review. The system automates execution by breaking down the plan into independent tasks, requiring a structured document to guide the specialized implementer subagents through the two-stage review process.