subagent-driven-development

Dispatch subagents for implementation, spec verification, and code quality review.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/smrik/ai-fund --skill subagent-driven-development-smrik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/smrik/ai-fund/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/smrik/ai-fund --skill subagent-driven-development-smrik

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of maintaining high code quality and spec compliance during complex, multi-task development sessions by automating the delegation and review process.

Core Features & Use Cases

  • Autonomous Task Execution: Dispatches specialized subagents for implementation, spec verification, and code quality review.
  • Two-Stage Review Loop: Ensures every task passes both a spec compliance check and a code quality audit before being marked as complete.
  • Use Case: When working on a multi-part feature plan, use this skill to automatically cycle through implementation and review phases for each task, ensuring that no requirement is missed and code quality remains high without manual intervention.

Quick Start

Initiate the subagent-driven-development process by providing the implementation plan file and requesting the execution of the first task in the current session.

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 code review and spec compliance for multi-task development workflows?

Automate code review and spec compliance by dispatching autonomous subagents for implementation and iterative review, ensuring every task passes a two-stage review loop before completion.

What is the best way to enforce automated TDD during a complex software engineering session?

Enforce automated TDD by orchestrating specialized subagents that handle implementation, spec verification, and code quality auditing within a single session, satisfying strict testing requirements.

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

A two-stage review loop dispatches independent subagents to execute implementation tasks, then forces each task through both a spec compliance check and a code quality audit before marking it complete.

Can I use subagent-driven development for multi-part feature plans without manual code review intervention?

Yes, subagent-driven development automatically cycles through implementation and review phases for multi-part feature plans, ensuring requirements are met and code quality remains high without manual intervention.

Do I need a specific implementation plan format to start autonomous task execution with subagents?

You need to provide an implementation plan file to initiate the subagent-driven development process, which then dispatches subagents to execute the first task in the current session.

When should I avoid using autonomous subagents for software engineering workflows?

Avoid using autonomous subagents for simple, single-step tasks that do not require strict adherence to complex implementation plans or automated spec compliance verification to prevent unnecessary overhead.