skills.rest
loganylchen
loganylchenCOMMUNITY
Explore all skills by this author →
Website𝕏@logan_cylGitHub

subagent-driven-development

Dispatch subagents to execute implementation tasks with two-stage spec and code quality reviews.

Updated Feb 3, 2026
Search Tags:#code quality#automation#testing#development#subagents#implementation plan
One-click install
npx skills add https://github.com/loganylchen/skills --skill subagent-driven-development-loganylchen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/loganylchen/skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/loganylchen/skills --skill subagent-driven-development-loganylchen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the development process by automating the execution of implementation plans, ensuring high-quality code through a structured, multi-stage review process within a single session.

Core Features & Use Cases

  • Automated Task Execution: Breaks down an implementation plan into independent tasks, assigning a fresh subagent to each.
  • Two-Stage Review: Implements a rigorous review process after each task: first for spec compliance, then for code quality.
  • Use Case: When you have a detailed feature plan with several distinct development tasks, use this Skill to have AI agents implement, test, and review each task sequentially, ensuring adherence to specifications and code quality standards before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at /path/to/your/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 implementation plan execution for multiple development tasks?▼

A two-stage code review process ensures high-quality code by first verifying spec compliance and then evaluating code quality. Each task implemented by a subagent undergoes this rigorous review before the session proceeds to the next task.

How does subagent-driven development enforce code quality during task execution?▼

A two-stage code review process ensures high-quality code by first verifying spec compliance and then evaluating code quality. Each task implemented by a subagent undergoes this rigorous review before the session proceeds to the next task.

What is the best way to implement a feature plan using TDD and AI subagents?▼

The best way to implement a feature plan with TDD is to use subagents that follow defined prompt templates. Independent subagents execute each task sequentially, adhering to TDD practices and undergoing automated spec and quality reviews within one session.

Do I need a detailed implementation plan before starting automated code generation?▼

The skill breaks down this plan into independent tasks, assigning a fresh subagent to execute each specific development requirement.

Can I execute multiple independent development tasks within a single session?▼

The system manages task execution sequentially, dispatching a subagent per task and running a two-stage review process for rapid, high-quality iteration.

Why does my automated development workflow require defined prompt templates?▼

These templates enforce TDD adherence, spec compliance, and code quality standards throughout the execution session.

Related Skills

Explore More Software Engineering Skills→
barretstorckbarretstorck
58

writing-plans

Generate step-by-step implementation plans for software development tasks.

Community
Intermediate
millioncomillionco
14.3k

ship

Coordinates review, refactoring, version control, and PR creation for branches.

Official
Advanced
alffeialffei
69

writing-plans

Generate implementation plans for multi-step software tasks with date-based filenames.

Community
Basic
pynbj1001pynbj1001
4

subagent-driven-development

Dispatch subagents for parallel tasks with two-stage reviews.

Community
Advanced