subagent-driven-development

Dispatch AI subagents to execute implementation tasks and review code.

Updated Jan 30, 2026

Search Tags:#code review #task management #development workflow #code generation #ai agents #iterative development

Ready to run

npx skills add https://github.com/andrescardonas7/salchipapa-web --skill subagent-driven-development-andrescardonas7

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/andrescardonas7/salchipapa-web/tree/main/.cursor/skills/subagent-driven-development
Command: npx skills add https://github.com/andrescardonas7/salchipapa-web --skill subagent-driven-development-andrescardonas7

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 leveraging independent AI subagents for each task, ensuring high-quality code through a structured, multi-stage review process.

Core Features & Use Cases

Task Decomposition: Breaks down complex plans into manageable, independent tasks.
Subagent Dispatch: Assigns each task to a fresh AI subagent for focused implementation.
Two-Stage Review: Implements a rigorous review process including spec compliance and code quality checks after each task.
Iterative Refinement: Facilitates rapid iteration by allowing subagents to fix issues identified during reviews.
Use Case: Implementing a new feature from a detailed plan, where each part of the feature can be developed and reviewed independently, leading to faster delivery of a robust solution.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at /path/to/your/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 execute implementation plans using AI agents for iterative development?▼

Iterative development with AI agents executes implementation plans by dispatching independent subagents for each task, followed by a two-stage review process for spec compliance and code quality. It manages task execution within a single session, ensuring context preservation and efficient iteration.

What is the two-stage review process for code generation in AI-driven development?▼

The two-stage review process in AI-driven development rigorously checks spec compliance and code quality after each task is implemented by a subagent. This structured review facilitates rapid iterative refinement by allowing the implementer agents to fix identified issues.

How to decompose complex development plans into manageable tasks for AI subagents?▼

Decomposing complex development plans into manageable tasks for AI subagents involves breaking down the plan into independent, focused units. Each task is then assigned to a fresh AI subagent, ensuring focused implementation and context preservation within a single session.

Does subagent-driven development support automated testing and self-review?▼

Yes, subagent-driven development supports automated testing and self-review by implementer agents. It facilitates rapid iteration by allowing subagents to fix issues identified during the rigorous two-stage review process for spec compliance and code quality.

What's the best way to maintain context when dispatching multiple AI agents for code implementation?▼

The best way to maintain context when dispatching multiple AI agents is to manage task execution within a single session. This subagent-driven approach ensures context preservation and efficient iteration by assigning each independent task to a fresh, focused subagent.