subagent-driven-development

Dispatch subagents with isolated context for two-stage task reviews.

Updated Apr 27, 2026
One-click install
npx skills add https://github.com/luiztrilha/dunderia-public --skill subagent-driven-development-luiztrilha
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/luiztrilha/dunderia-public/tree/main/templates/local-runtime-profile/skills/superpowers/subagent-driven-development
Command: npx skills add https://github.com/luiztrilha/dunderia-public --skill subagent-driven-development-luiztrilha

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines task execution by dispatching fresh subagents for independent tasks, ensuring focused work and high-quality iteration.

Core Features & Use Cases

  • Subagent Dispatch: Assign tasks to specialized subagents, preserving session context and isolating context for each task.
  • Two-Stage Review: Perform spec compliance and code quality reviews to ensure high standards of work.
  • Use Case: Ideal for executing implementation plans with independent tasks, where maintaining high-quality output is critical.

Quick Start

Use the subagent-driven-development skill to execute the "feature-plan.md" with subagent-driven development.

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 an implementation plan with isolated context for each task?

You execute an implementation plan by dispatching fresh subagents for independent tasks, preserving your main session context while isolating each task to ensure focused work and high-quality iteration.

What is subagent-driven development and how does it handle task execution?

Subagent-driven development is a task execution process that dispatches specialized subagents for implementation, followed by a mandatory two-stage review for specification compliance and code quality on each task.

How do I automate code review and spec compliance for independent coding tasks?

Automate code review by coordinating specialized agents that perform a two-stage review, checking both specification compliance and overall code quality after a subagent completes an isolated implementation task.

Can I run multiple independent implementation tasks within a single development session?

Yes, you can manage multiple independent tasks within a single session by dispatching fresh subagents for each task, which preserves your main session context while isolating the work environment for focused execution.

What is the best way to maintain code quality when dispatching multiple subagents?

Maintain code quality by enforcing a two-stage review process where specialized agents evaluate specification compliance and code quality for every task completed by an isolated subagent during iterative development.