subagent-driven-development

Dispatch subagents for implementation tasks and review spec compliance and code quality.

Updated Aug 23, 2026

Search Tags:#code review #development workflow #task automation #ai agents #iterative development #subagent

Ready to run

npx skills add https://github.com/pearjelly/turbooknow --skill subagent-driven-development-pearjelly

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/pearjelly/turbooknow/tree/main/.agent/skills/subagent-driven-development
Command: npx skills add https://github.com/pearjelly/turbooknow --skill subagent-driven-development-pearjelly

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes 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, ensuring high quality through rigorous, multi-stage reviews.

Core Features & Use Cases

Task Decomposition: Automatically breaks down a development plan into manageable, independent tasks.
Subagent Dispatch: Assigns a fresh AI subagent for each task to ensure clean context.
Two-Stage Review: Implements a mandatory spec compliance review followed by a code quality review for every task.
Iterative Refinement: Manages feedback loops between implementer and reviewer agents until tasks meet all criteria.
Use Case: Executing a complex feature development plan where each API endpoint, UI component, or backend logic piece is a distinct task, ensuring each part is spec-compliant and well-coded before integration.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan found in the file 'docs/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 iterative development with AI agents for complex implementation plans?▼

Iterative development with AI agents is automated by breaking down implementation plans into independent tasks, dispatching a dedicated subagent for each task, and running two-stage reviews for spec compliance and code quality. Feedback loops manage iterative refinement until all criteria are met.

How does subagent dispatch work for task decomposition in development workflows?▼

Subagent dispatch works by assigning a fresh AI subagent to each independently decomposed task from a development plan. This ensures clean context per task before proceeding to mandatory spec compliance and code quality reviews.

What is the best way to ensure code quality and spec compliance during AI-driven code generation?▼

The best way to ensure code quality and spec compliance is implementing a mandatory two-stage review process where a reviewer agent checks spec compliance first, then code quality, managing feedback loops with the implementer agent until tasks pass.

Can I use AI agents to execute an implementation plan found in a markdown file?▼

Yes, you can use AI agents to execute an implementation plan found in a markdown file. The skill reads the plan file, decomposes it into independent tasks, and dispatches subagents to handle each task within a single session.

Do I need to manually review code when using AI subagents for task automation?▼

Manual code review is minimized because the workflow mandates automated two-stage reviews for spec compliance and code quality. Reviewer agents run iterative feedback loops with implementer agents to automatically refine tasks until they meet all criteria.

Why use independent subagents for each task instead of a single AI agent for the whole plan?▼

Independent subagents are used for each task to ensure clean context isolation. This approach prevents context bleeding across tasks, allowing dedicated agents to focus on specific API endpoints or UI components before multi-stage reviews validate integration.