Can this skill handle Test-Driven Development?

Absolutely. Subagents are specifically instructed to write tests and verify their implementation using TDD principles as part of their reporting process.

What happens if a subagent fails a task?

Instead of manual fixing, the workflow suggests dispatching a specific fix subagent with the review feedback, keeping the primary session context clean and focused.

Is code review mandatory in this workflow?

Yes. The skill is designed to automatically dispatch a code-reviewer subagent after every task. You cannot proceed to the next task until the review is complete and critical issues are addressed.

How does Subagent-Driven Development prevent context pollution?

It dispatches a completely fresh subagent for every individual task in your plan. This ensures the AI doesn't get confused by previous errors, unrelated files, or accumulated chat history from earlier tasks.

When should I use this over standard plan execution?

Use this skill when you want to stay in your current session and have tasks that are mostly independent. It provides faster iteration with more frequent quality checks than manual execution.

Subagent-Driven Development

Name: Subagent-Driven Development
Author: seanGSISG

byseanGSISG

生产力与工作流

Executes complex implementation plans by dispatching fresh subagents for independent tasks with automated quality gates between each step.

关于

Subagent-Driven Development is a workflow optimization skill designed to handle multi-task implementation plans with high precision and minimal context drift. By dispatching a fresh, ephemeral subagent for every individual task, the skill ensures that each unit of work is performed in a clean environment, preventing context pollution. It enforces a rigorous 'Quality Gate' architecture where every task implementation must pass a mandatory code review by a specialized reviewer subagent before the workflow proceeds. This approach combines the speed of automated iteration with the reliability of structured oversight, making it ideal for complex feature development and large-scale refactoring within a single session.

主要功能

Final Architecture Validation: Performs a comprehensive final review once all plan requirements are met.
TDD Integration: Instructs subagents to follow Test-Driven Development patterns for verified results.
Feedback Loop Management: Automatically dispatches follow-up agents to resolve issues found during review.
Task Isolation: Dispatches fresh subagents for every task to prevent context pollution and AI drift.
Automated Quality Gates: Mandates specialized code reviews after each task completion.
0 GitHub stars

使用场景

Building production-grade software where mandatory peer review is required for every commit.
Executing a multi-feature development roadmap within a single session without losing accuracy.
Performing complex refactoring where each module requires isolated testing and verification.

关于

主要功能

Final Architecture Validation: Performs a comprehensive final review once all plan requirements are met.
TDD Integration: Instructs subagents to follow Test-Driven Development patterns for verified results.
Feedback Loop Management: Automatically dispatches follow-up agents to resolve issues found during review.
Task Isolation: Dispatches fresh subagents for every task to prevent context pollution and AI drift.
Automated Quality Gates: Mandates specialized code reviews after each task completion.
0 GitHub stars

使用场景

Building production-grade software where mandatory peer review is required for every commit.
Executing a multi-feature development roadmap within a single session without losing accuracy.
Performing complex refactoring where each module requires isolated testing and verification.