subagent-driven-development

Execute development plans by dispatching AI subagents for implementation and review.

Updated Mar 26, 2025
One-click install
npx skills add https://github.com/GSU-FrankJ/tournament_experiment --skill subagent-driven-development-gsu-frankj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/GSU-FrankJ/tournament_experiment/tree/main/.cursor/skills/subagent-driven-development
Command: npx skills add https://github.com/GSU-FrankJ/tournament_experiment --skill subagent-driven-development-gsu-frankj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the implementation of development plans by orchestrating independent AI subagents for each task, ensuring high-quality code through a rigorous two-stage review process.

Core Features & Use Cases

  • Task Decomposition: Breaks down a larger plan into discrete, manageable tasks.
  • Subagent Orchestration: Dispatches specialized AI agents for implementation, spec review, and code quality checks.
  • Two-Stage Review: Enforces compliance with specifications first, followed by a code quality assessment.
  • Iterative Refinement: Manages feedback loops between reviewers and implementers until all issues are resolved.
  • Use Case: When you have a detailed feature plan, this Skill can autonomously execute each step, from writing the code to ensuring it meets all requirements and quality standards, without manual intervention between tasks.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at docs/plans/new-feature.md.

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 iterative development with AI agents for a feature plan?

Automated iterative development dispatches independent AI subagents for each task, followed by sequential spec compliance and code quality reviews. It manages feedback loops between agents to ensure task completion and quality standards within a single session.

What is the best way to orchestrate AI subagents for task execution and code review?

Orchestrating AI subagents involves dispatching specialized agents for implementation, spec review, and code quality checks. A two-stage review process enforces specification compliance first, followed by iterative refinement through automated feedback loops until issues resolve.

Do I need a detailed development plan before using AI agent orchestration?

Yes, you need a detailed development plan to execute tasks autonomously. The process breaks down a larger plan into discrete, manageable tasks, dispatching agents for implementation and review without requiring manual intervention between steps.

How does the two-stage review process work for AI-generated code?

The two-stage review process for AI-generated code enforces compliance with specifications first, followed by a code quality assessment. It manages iterative feedback loops between reviewers and implementers until all quality issues are resolved.

Can I use agent orchestration to manage feedback loops between implementation and review agents?

Yes, agent orchestration manages iterative feedback loops between implementation and review agents. It coordinates automated spec compliance and code quality reviews until all issues are resolved, ensuring high-quality software development within a single session.

What are the limitations of using subagent orchestration for software development?

Subagent orchestration operates within a single development session and requires a pre-existing detailed feature plan. It manages task decomposition and iterative feedback loops but cannot generate the initial development plan autonomously.