subagent-driven-development

Dispatch independent subagents for each task and run two-stage reviews.

34|5|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/weiping/pi-superpowers --skill subagent-driven-development-weiping
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/weiping/pi-superpowers/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/weiping/pi-superpowers --skill subagent-driven-development-weiping

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 a dedicated subagent with rigorous, multi-stage reviews.

Core Features & Use Cases

  • Task Decomposition: Executes plans by dispatching a fresh subagent for each independent task.
  • Two-Stage Review: Ensures quality through mandatory spec compliance and code quality reviews after each task.
  • Use Case: When developing a new feature with multiple distinct components, this skill ensures each component is implemented, tested, and reviewed systematically before moving to the next, preventing integration issues and maintaining high code quality.

Quick Start

Use the subagent-driven-development skill to execute the plan outlined in the provided document.

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 by breaking it into independent tasks?

Executing implementation plans with independent tasks is done by dispatching a dedicated subagent for each task. This approach manages task decomposition and subagent coordination within the same session to maintain context and enable fast iteration.

How does subagent coordination handle code review during development workflows?

Subagent coordination handles code review through a mandatory two-stage process. After each task is executed, it enforces spec compliance and code quality reviews to prevent integration issues and maintain robust software development workflows.

What is the best way to ensure spec compliance when developing multiple feature components?

Ensuring spec compliance for multiple components is best handled by a two-stage review process. Each task undergoes mandatory spec compliance and code quality reviews before moving to the next, preventing integration issues systematically.

Do I need to provide a detailed plan document to use subagent-driven development?

You need to provide an implementation plan document outlining the tasks. The skill executes the plan by dispatching a fresh subagent for each independent task within the same session to maintain context and ensure fast iteration.

Can I use this task execution approach for TDD workflows?

You can use this approach for TDD workflows. It executes plans by dispatching subagents for each task and enforces mandatory two-stage reviews, ensuring each component is implemented, tested, and reviewed before proceeding.