subagent-driven-development

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

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/zhou533/UnVault --skill subagent-driven-development-zhou533
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/zhou533/UnVault/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/zhou533/UnVault --skill subagent-driven-development-zhou533

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the implementation of complex plans by breaking them down into independent tasks, each handled by a dedicated subagent with a rigorous two-stage review process, ensuring high quality and rapid iteration.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a larger plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns each task to a fresh "implementer" subagent.
  • Two-Stage Review: Enforces a spec compliance review followed by a code quality review for each task.
  • Iterative Refinement: Manages review loops, ensuring issues are fixed before proceeding.
  • Use Case: Implementing a new feature requires multiple distinct steps like setting up database schemas, building API endpoints, and creating UI components. This Skill ensures each step is completed correctly and efficiently before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan outlined in the attached document 'feature-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 manage iterative development tasks for a complex feature plan?

Iterative development for a complex feature plan is managed by breaking it into independent tasks, dispatching a fresh subagent for each, and enforcing a two-stage review process for spec compliance and code quality.

What is a two-stage code review process for subagent-driven development?

A two-stage code review process enforces spec compliance first, followed by a dedicated code quality review, ensuring each subagent's implementation meets requirements before proceeding to the next task.

Can I use iterative development subagents to implement multi-step features like APIs and UI components?

Yes, iterative development subagents can implement multi-step features by assigning distinct steps like database schemas, API endpoints, and UI components to independent subagents within a single development session.

What is the best way to ensure spec compliance during rapid iterative development?

The best way to ensure spec compliance during rapid iterative development is using automated review loops that manage iterative refinement, ensuring issues are fixed before moving to the next task.

Why does task implementation stall when managing multiple complex steps without subagents?

Task implementation stalls without subagents because a single context cannot effectively decompose plans, implement distinct steps, and maintain code quality simultaneously across an entire development session.