skills.rest
shynlee04
shynlee04COMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Delegate independent implementation tasks to AI subagents with two-stage reviews.

Updated Feb 5, 2026
Search Tags:#code quality#prompt engineering#software development#ai agents#iterative development#task execution
One-click install
npx skills add https://github.com/shynlee04/idumb-v2 --skill subagent-driven-development-shynlee04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/shynlee04/idumb-v2/tree/main/.agent/skills%20copy/subagent-driven-development
Command: npx skills add https://github.com/shynlee04/idumb-v2 --skill subagent-driven-development-shynlee04

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the execution of complex implementation plans by breaking them down into independent tasks, each handled by specialized AI subagents with rigorous review stages, ensuring high quality and rapid iteration.

Core Features & Use Cases

  • Task Decomposition: Executes plans by dispatching independent subagents for each task.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for every task.
  • Iterative Improvement: Facilitates rapid iteration through automated review loops and subagent-driven fixes.
  • Use Case: When you have a detailed feature plan with multiple distinct development tasks, this Skill can manage the entire implementation process, from initial coding to final review, ensuring each part meets specifications and quality standards before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at './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 execute complex implementation plans with AI agents?▼

Executing complex implementation plans with AI agents involves breaking them down into independent tasks, dispatching specialized subagents for each task, and running iterative two-stage reviews for spec compliance and code quality.

What is two-stage review in iterative software development?▼

Two-stage review in iterative software development is an automated process where a spec compliance review is followed by a code quality review for every task, ensuring subagent-driven fixes meet specifications before iteration continues.

How do I ensure code quality when delegating tasks to specialized AI subagents?▼

To ensure code quality when delegating tasks to specialized AI subagents, orchestrate the execution with a two-stage review process that automates spec compliance checks and code quality reviews within a single session.

Do I need prompt templates to manage task decomposition with AI agents?▼

Yes, managing task decomposition with AI agents requires prompt templates for the implementer, spec reviewer, and code quality reviewer subagents to properly orchestrate execution and maintain iterative development cycles.

What's the best way to automate spec compliance checks for independent development tasks?▼

The best way to automate spec compliance checks for independent development tasks is to use a subagent-driven approach that dispatches specialized reviewers to evaluate each task against the plan before moving to the next iteration.

Can I manage iterative development cycles for multiple tasks in a single session?▼

Yes, you can manage iterative development cycles for multiple tasks in a single session by orchestrating specialized AI subagents that handle task execution, spec compliance reviews, and code quality fixes automatically.

Related Skills

Explore More Software Engineering Skills→
guanyangguanyang
947

subagent-driven-development

Execute implementation plans by dispatching subagents for tasks and reviewing spec compliance and code quality.

Community
Advanced
liamtran96liamtran96

requesting-code-review

Dispatch a code-reviewer subagent to assess code quality, architecture, testing, and production readiness.

Community
Basic
oteroweboteroweb

subagent-driven-development

Delegate each development task to a fresh subagent with two-stage reviews.

Community
Advanced
tassiovaletassiovale
13

subagent-driven-development

Dispatches subagents to execute implementation plan tasks with two-stage reviews.

Community
Advanced