skills.rest
nilecui
nilecuiCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

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

27|10|Updated Dec 27, 2025
Search Tags:#code quality#workflow#development#agent#implementation plan#iterative
One-click install
npx skills add https://github.com/nilecui/SkillsBase --skill subagent-driven-development-nilecui
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/nilecui/SkillsBase/tree/main/.cursor/skills/subagent-driven-development
Command: npx skills add https://github.com/nilecui/SkillsBase --skill subagent-driven-development-nilecui

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 and rapid iteration within a single session.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a larger plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns a fresh AI subagent to each task for focused implementation.
  • Two-Stage Review: Implements a mandatory spec compliance review followed by a code quality review for each task.
  • Iterative Refinement: Manages loops for fixing issues identified during reviews.
  • Use Case: When you have a detailed feature plan, this Skill will manage the AI agents to build each part of the feature, ensuring it 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 ./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 from an implementation plan?▼

Iterative development with AI agents works by breaking down a plan into independent tasks, dispatching a subagent per task, and enforcing spec compliance and code quality reviews. This manages task decomposition and refinement loops for rapid cycles.

What is the best way to ensure code quality when using AI agents for feature implementation?▼

The best way to ensure code quality with AI agents is a two-stage review process. After a subagent completes a task, enforce a mandatory spec compliance review followed by a code quality review within the current session.

How does subagent task decomposition work for complex implementation plans?▼

Task decomposition for implementation plans works by automatically breaking down a large plan into manageable, independent tasks. Each task is assigned to a dedicated, fresh AI subagent for focused implementation and iterative refinement.

Can I use AI agents to manage iterative refinement loops during a development session?▼

Yes, you can use AI agents to manage iterative refinement loops. The process dispatches subagents per task and automatically manages loops to fix issues identified during mandatory spec compliance and code quality reviews.

Do I need a detailed implementation plan before starting AI agent driven development?▼

Yes, you need a detailed implementation plan file before starting AI agent driven development. The process executes the plan by dispatching independent subagents per task and managing iterative refinement to ensure high-quality outputs.

Related Skills

Explore More Software Engineering Skills→
tukuyomil032tukuyomil032
2

writing-plans

Automate detailed implementation plans with Markdown and structured task decomposition.

Community
Advanced
ReinaMacCredyReinaMacCredy
223

finishing-a-development-branch

Verify tests and present merge, PR, or cleanup options for a development branch.

Community
Advanced
gztcodegztcode

requesting-code-review

Automate code review with static security scanning, quality gates, and an independent reviewer subagent.

Community
Advanced
AlphaLab-USTCAlphaLab-USTC
131

subagent-driven-development

Execute implementation plans by delegating tasks to fresh subagents with spec and code quality reviews.

Community
Advanced