subagent-driven-development

Execute development tasks via subagents with a two-stage review process.

Updated May 8, 2026
One-click install
npx skills add https://github.com/superfhp/lumi-agent --skill subagent-driven-development-superfhp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/superfhp/lumi-agent/tree/main/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/superfhp/lumi-agent --skill subagent-driven-development-superfhp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenges of implementing complex development plans by providing a systematic approach to task execution and review, ensuring high-quality, fast iteration.

Core Features & Use Cases

  • Task Execution: Execute implementation plans by dispatching fresh subagents per task.
  • Two-Stage Review: Ensures spec compliance and code quality through a two-stage review process.
  • Use Case: Ideal for large development projects where tasks are mostly independent and quality and spec compliance are crucial.

Quick Start

Dispatch a new subagent to implement a task from your plan using the 'delegate_task' command.

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 development task execution to ensure spec compliance?

Automate development task execution by dispatching fresh subagents per task and applying a two-stage review process to verify spec compliance and code quality, ensuring fast iteration on complex plans.

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

A two-stage review process systematically checks both spec compliance and code quality after task execution, ensuring that fresh subagents implementing independent tasks meet the required standards before integration.

How do I delegate tasks to subagents for independent development modules?

Delegate tasks to subagents by using the delegate_task command, which dispatches a new subagent to implement each specific task from your plan and executes it systematically.

Do I need Python to run script-based task execution and review?

Yes, you need Python and the ability to execute script-based tasks to use this systematic task execution and two-stage review process for your development workflow.

When should I use subagent-driven development for my project?

Use subagent-driven development for large projects where implementation tasks are mostly independent, and where strict code quality and spec compliance are crucial for high-quality iteration.

What is the best way to manage code quality across multiple independent tasks?

Manage code quality by dispatching fresh subagents per task and enforcing a two-stage review process that validates both spec compliance and code quality for each independent module.