subagent-driven-development

Execute implementation plans by dispatching fresh subagents for each task with two-stage reviews.

Updated May 21, 2026
One-click install
npx skills add https://github.com/shades-of-web/skills --skill subagent-driven-development-shades-of-web
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/shades-of-web/skills/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/shades-of-web/skills --skill subagent-driven-development-shades-of-web

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps in executing implementation plans with independent tasks in the current session, ensuring high quality and fast iteration through fresh subagents and two-stage reviews.

Core Features & Use Cases

  • Independent Task Execution: Assigns a fresh subagent per task to maintain a clean context and avoid interference.
  • Two-Stage Review: Ensures code meets specifications and adheres to quality standards through a two-step review process.
  • Use Case: Ideal for development workflows where tasks are mostly independent and need to be executed within the same session.

Quick Start

Use the subagent-driven-development skill to execute your implementation plan by dispatching fresh subagents for each task, followed by spec and code quality reviews.

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 independent implementation tasks without context interference?

Executing independent implementation tasks without context interference is done by dispatching a fresh subagent per task, ensuring a clean environment and preventing interference from prior task data.

What is subagent-driven development and how does it maintain spec compliance?

Subagent-driven development is a workflow that dispatches fresh subagents for each task and maintains spec compliance through a two-stage review process checking both specifications and code quality standards.

How to ensure code quality when running multiple development tasks in the same session?

Ensuring code quality when running multiple development tasks in the same session requires a two-stage review process that evaluates both spec compliance and quality standards after each fresh subagent executes its assigned task.

Does subagent-driven development work for tasks with dependencies between each other?

Subagent-driven development is ideal for development workflows where tasks are mostly independent, making it less suitable for tightly coupled tasks that require continuous shared context and state management.

What's the best way to dispatch subagents for independent development workflows?

The best way to dispatch subagents for independent development workflows is assigning a fresh subagent per task to maintain a clean context, followed by a two-stage review for spec and code quality verification.