How does this differ from standard plan execution?

Unlike standard execution, this skill dispatches a fresh subagent for every task within the same session to prevent context pollution and adds mandatory code review steps after every task.

When should I avoid using Subagent-Driven Development?

Avoid this skill if your tasks are tightly coupled and require manual intervention, or if your implementation plan hasn't been fully finalized and reviewed yet.

Does this skill support Test-Driven Development?

Yes, subagents are explicitly instructed to follow TDD principles, writing and verifying tests for each task they implement.

What happens if a subagent fails a task?

If issues are found during the review phase, a fix subagent is dispatched with specific instructions to resolve the problems before the workflow moves to the next task.

Subagent-Driven Development

Name: Subagent-Driven Development
Author: AlabamaMike

byAlabamaMike

0•

生产力与工作流

Executes multi-task implementation plans by dispatching specialized subagents for each step with integrated code reviews.

Subagent-Driven Development streamlines complex coding projects by breaking implementation plans into independent tasks handled by fresh AI subagents. By isolating context for each task and enforcing mandatory code reviews between steps, it prevents context pollution and ensures high-quality code output without requiring constant human intervention. This skill is ideal for developers staying within a single session who want to iterate rapidly while maintaining rigorous quality gates, TDD standards, and architectural consistency.

主要功能

01Seamless integration with Test-Driven Development (TDD) workflows

02Automated quality gates with mandatory code reviews between implementation steps

03Context isolation through fresh subagent dispatch for every individual task

04Final architectural validation and automated branch finalization

05Continuous progress tracking using TodoWrite for transparent task management

060 GitHub stars

使用场景

01Enforcing high-quality standards through automated peer review cycles during active development

02Rapidly iterating on independent modules without manual context switching

03Executing complex multi-file feature implementations from a pre-written plan

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add alabamamike/copilot-agents subagent-driven-development

For use in Claude.ai and ChatGPT

Download Skill