subagent-driven-development

Dispatch independent subagents to execute implementation plans with two-stage reviews.

4|Updated May 14, 2026
One-click install
npx skills add https://github.com/liumeixin/hermes-skills --skill subagent-driven-development-liumeixin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/liumeixin/hermes-skills/tree/main/software-development/subagent-driven-development
Command: npx skills add https://github.com/liumeixin/hermes-skills --skill subagent-driven-development-liumeixin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of executing complex implementation plans with independent tasks, ensuring high-quality, fast iteration through systematic two-stage reviews.

Core Features & Use Cases

  • Task Dispatch: Dispatches fresh subagents for each task, maintaining a clean context.
  • Two-Stage Review: Ensures spec compliance and code quality through separate reviews.
  • Use Case: Ideal for implementing software development plans where tasks are independent and quality is critical, such as in a team-based development environment.

Quick Start

Use the subagent-driven-development skill to start implementing your plan by dispatching a task for 'Create User model with email field'.

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 task execution for an implementation plan using subagents?

Automating task execution with subagents involves dispatching a fresh independent agent for each task in your implementation plan to maintain a clean context. This approach systematically automates software development plans by isolating task execution environments.

What is a two-stage review process in software development?

A two-stage review process in software development separates spec compliance verification from code quality checks. It ensures implementation plans meet technical specifications first, then validates overall code quality through independent automated reviews.

Do I need Python to run subagent-driven task dispatch and reviews?

Yes, you need Python installed in your environment to run subagent-driven task dispatch and reviews. Python is required specifically for managing the task dispatch logic and executing the two-stage review process scripts.

How to ensure code quality when implementing independent software development tasks?

To ensure code quality for independent software development tasks, dispatch fresh subagents for each task and apply a two-stage review process. This separates spec compliance validation from general code quality checks for fast iteration.

When should I use independent subagents for implementation plan execution?

Use independent subagents for implementation plan execution when tasks are completely independent and quality is critical. This approach is ideal for team-based development environments requiring fast iteration and systematic spec compliance verification.

What's the best way to maintain clean context during software development task execution?

The best way to maintain clean context during software development task execution is dispatching fresh independent subagents for each individual task. This prevents context bleeding between tasks while ensuring systematic two-stage reviews for code quality.