subagent-driven-development

Dispatch AI subagents to implement tasks and review spec compliance and code quality.

Updated Jan 15, 2026
One-click install
npx skills add https://github.com/lips85/antigravity-skills-bootstrap --skill subagent-driven-development-lips85
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/lips85/antigravity-skills-bootstrap/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/lips85/antigravity-skills-bootstrap --skill subagent-driven-development-lips85

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the development process by breaking down implementation plans into independent tasks, each handled by a dedicated AI subagent with rigorous review stages.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns each task to a fresh AI subagent for implementation.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for each task.
  • Iterative Refinement: Manages feedback loops where subagents fix issues identified during reviews.
  • Use Case: Implementing a new feature from a detailed plan, ensuring each part is spec-compliant and well-coded before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./docs/plans/feature-plan.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 implementation plan execution with AI subagents?

Subagent-driven development automates plan execution by decomposing plans into independent tasks, dispatching dedicated AI subagents for implementation, and running two-stage reviews with iterative feedback loops for spec compliance and code quality.

What is the two-stage AI code review process for iterative development?

The two-stage AI code review process first checks spec compliance against the implementation plan, then evaluates code quality, managing iterative refinement through feedback loops between implementer and reviewer subagents within the same session.

How do I break down a feature plan into independent tasks for AI execution?

Breaking down a feature plan for AI execution involves task decomposition, where the plan is split into manageable independent tasks, each assigned to a fresh subagent that implements and refines the code through automated review stages.

Can I use AI workflow subagents to manage iterative code refinement?

Yes, you can use AI workflow subagents to manage iterative code refinement by running feedback loops where implementer subagents fix issues identified by reviewer subagents, ensuring each task is spec-compliant before moving to the next.

What are the limitations of using subagent-driven development for task execution?

Subagent-driven development requires a detailed implementation plan as input and processes tasks sequentially within a single session, meaning it is designed for structured feature implementation rather than open-ended exploratory coding without a predefined plan.