skills.rest
minseok1109
minseok1109COMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch AI subagents to implement development plan tasks with two-stage reviews.

Updated Jun 13, 2025
Search Tags:#development#code review#ai agents#implementation plan#iterative development#task execution
One-click install
npx skills add https://github.com/minseok1109/coffimer-app --skill subagent-driven-development-minseok1109
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/minseok1109/coffimer-app/tree/main/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/minseok1109/coffimer-app --skill subagent-driven-development-minseok1109

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 review stages, ensuring high-quality code and efficient iteration.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a development plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns each task to a fresh AI subagent for focused implementation.
  • Two-Stage Review: Implements a dual review process: first for spec compliance, then for code quality.
  • Iterative Refinement: Manages feedback loops for fixing issues identified during reviews.
  • Use Case: When you have a complex feature requirement, this Skill can manage the entire implementation, from initial coding to final review, by orchestrating multiple AI agents.

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 a complex implementation plan using AI agents?▼

You can execute an implementation plan by dispatching independent AI subagents for each task. This approach breaks down development plans into manageable, isolated tasks for focused implementation.

What is the two-stage code review process for iterative development?▼

The two-stage review process evaluates task implementation first for spec compliance and then for code quality. This ensures the generated code meets both functional requirements and quality standards.

How do I manage feedback loops when fixing issues found during AI code review?▼

Iterative refinement manages feedback loops by routing identified issues back to the task execution cycle. This allows the AI subagents to resolve code quality and spec compliance problems within a single session.

Can I use subagent-driven development for multi-task feature implementation?▼

Yes, subagent-driven development orchestrates multi-task feature implementation by assigning each decomposed task to a fresh AI subagent. This ensures task isolation and context preservation throughout the workflow.

What are the limitations of using AI subagents for task decomposition?▼

The approach relies on a single session for iterative development and task execution. It requires a pre-defined implementation plan file to function, limiting its use for ad-hoc or unstructured coding tasks.

Related Skills

Explore More Software Engineering Skills→
zhexulongzhexulong
5

subagent-driven-development

Dispatch specialized subagents to implement, test, and review development tasks.

Community
Advanced
tomzxtomzx
5

directory-to-spec

Generate one RFC-2119 spec file per major feature from a codebase.

Community
Intermediate
jpeggdevjpeggdev

delegate

Execute implementation plans by dispatching subagents with two-stage reviews.

Community
Advanced
roderikroderik
2

subagent-driven-development

Dispatch fresh subagents per task to execute implementation plans with two-stage reviews.

Community
Advanced