subagent-driven-development

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

1|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/bailynlove/STARK-TOWER --skill subagent-driven-development-bailynlove
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/bailynlove/STARK-TOWER/tree/main/opencrew/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/bailynlove/STARK-TOWER --skill subagent-driven-development-bailynlove

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the execution of implementation plans with independent tasks, ensuring high-quality, fast iteration through systematic two-stage review.

Core Features & Use Cases

  • Task Execution: Dispatches fresh subagents per task, ensuring no confusion from accumulated state.
  • Automated Review: Implements two-stage review for spec compliance and code quality.
  • Use Case: Ideal for executing implementation plans in software development, where tasks are independent and quality control is crucial.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan for the 'User Authentication' feature.

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 with independent subagents?

Automated task execution dispatches independent subagents for each task in an implementation plan, preventing state confusion. It uses two-stage review to enforce spec compliance and code quality during software development.

How does two-stage review work for subagent-driven development?

Two-stage review in subagent-driven development evaluates spec compliance and code quality sequentially. This automated mechanism ensures implementation plans meet critical software quality standards before finalizing task execution.

What is the best way to execute independent software development tasks without state confusion?

Executing independent tasks via fresh subagents per task eliminates accumulated state confusion. This subagent-driven approach maintains clear execution boundaries and ensures high-quality software development iteration.

Is subagent-driven development suitable for tightly coupled software tasks?

Subagent-driven development is designed for software development scenarios where tasks are largely independent. It is not suitable for tightly coupled tasks because it relies on dispatching independent subagents for isolated execution.

Do I need specific tools to dispatch subagents and conduct code review?

Yes, this automated task execution requires tools for task dispatch and code review. These tools enable the two-stage review process and the independent subagent dispatch needed for implementation plans.