subagent-driven-development

Dispatch fresh subagents for each task with two-stage spec and quality reviews.

Updated May 28, 2026
One-click install
npx skills add https://github.com/haryelramalho/skills --skill subagent-driven-development-haryelramalho
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/haryelramalho/skills/tree/main/skills/community/subagent-driven-development
Command: npx skills add https://github.com/haryelramalho/skills --skill subagent-driven-development-haryelramalho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of manually coordinating multi-step implementation work by splitting a plan into independent tasks, assigning each task to a fresh subagent, and keeping the session focused on execution instead of repeated human check-ins.

Core Features & Use Cases

  • Task-by-task delegation: Sends each plan item to a separate implementer subagent so work stays isolated and context remains clean.
  • Two-stage review: Verifies every task first for spec compliance and then for code quality before marking it complete.
  • Continuous execution: Keeps moving through the full plan until all tasks are done, unless a blocker or real ambiguity requires escalation.
  • Best for implementation plans: Ideal for feature delivery, refactors, and other workflows where tasks are mostly independent but still need tight quality control.

Quick Start

Use the subagent-driven-development skill to execute a prepared implementation plan by delegating each task to a fresh subagent and reviewing each result twice before continuing.

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 multi-step implementation plans without manual check-ins?

Automating implementation plans requires dispatching each task to a fresh subagent, enforcing two-stage reviews for spec compliance and code quality, and allowing continuous execution until all tasks are complete or a blocker requires escalation.

How does subagent task delegation keep development workflows isolated?

Subagent task delegation keeps workflows isolated by sending each plan item to a separate implementer subagent, ensuring context remains clean and work stays separated before undergoing strict code quality and spec compliance reviews.

What is the best way to enforce code review and spec compliance during automated feature delivery?

The best way to enforce spec compliance and code review during feature delivery is applying a two-stage review gating process that verifies every delegated subagent task against requirements before marking it complete and continuing execution.

Can I use subagent-driven development for refactoring tasks with mostly independent steps?

Yes, subagent-driven development is ideal for refactoring tasks and feature delivery where steps are mostly independent, as it delegates each task to a fresh subagent and maintains quality control through continuous two-stage reviews.

When should I not use subagents for implementation plan execution?

You should not use subagents for implementation plan execution when tasks have heavy interdependencies or require frequent human check-ins, as the workflow is designed for continuous execution without intermediate manual intervention.

Do I need a prepared implementation plan to start task delegation with subagents?

Yes, task delegation with subagents requires a prepared implementation plan with explicit task context to initiate execution, as the workflow splits the plan into independent items and dispatches a fresh subagent for each.