subagent-driven-development

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

18|8|Updated May 31, 2023
One-click install
npx skills add https://github.com/jpmorgan-payments/embedded-finance --skill subagent-driven-development-jpmorgan-payments
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/jpmorgan-payments/embedded-finance/tree/main/.github/skills/superpowers/subagent-driven-development
Command: npx skills add https://github.com/jpmorgan-payments/embedded-finance --skill subagent-driven-development-jpmorgan-payments

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes 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, ensuring high quality through a structured, two-stage review process.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a larger implementation plan 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: first, spec compliance, then code quality.
  • Iterative Refinement: Manages feedback loops where subagents fix issues identified during reviews.
  • Use Case: When you have a complex feature to build, this Skill can manage the entire implementation, from initial coding to final review, by orchestrating multiple AI agents.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan found in the file '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 manage complex implementation plans using AI agents for iterative development?

Subagent-driven development manages complex implementation plans by decomposing them into independent tasks, dispatching dedicated AI subagents for each task, and running a two-stage review for spec compliance and code quality.

How does AI task decomposition work for multi-step feature development?

AI task decomposition works by automatically breaking down a larger implementation plan into manageable, independent tasks, assigning each to a fresh subagent to manage dependencies, context, and iterative refinement within a single session.

What is the best way to automate code review and spec compliance for AI generated code?

Automating code review and spec compliance is best handled through a two-stage review process that first checks implementation against the spec, then evaluates code quality, feeding issues back to subagents for iterative refinement.

Can I execute an implementation plan from a markdown file using AI subagents?

Yes, you can execute an implementation plan from a markdown file by pointing the subagent-driven development workflow to your plan file, which orchestrates task execution, dependency management, and code review within a single session.

How do AI subagents handle task dependencies and context during code generation?

AI subagents handle task dependencies and context by receiving fresh, focused execution environments for each independent task, while the orchestrator manages the overall context, dependency order, and iterative feedback loops across the session.