skills.rest
LuizEduPP
LuizEduPPCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task with sequential spec and code reviews.

Updated Apr 10, 2026
Search Tags:#quality assurance#code review#workflow automation#implementation#subagents#task orchestration
One-click install
npx skills add https://github.com/LuizEduPP/skills --skill subagent-driven-development-luizedupp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/LuizEduPP/skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/LuizEduPP/skills --skill subagent-driven-development-luizedupp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It keeps implementation plans from corrupting the shared controller context while ensuring every independent task is fully verified before moving on, preventing drift and rework during execution.

Core Features & Use Cases

  • Fresh context per task: Dispatch a dedicated implementer subagent for each plan item so work never inherits stale history and can stay focused on a single responsibility.
  • Two-stage reviews: After each implementation, run spec compliance and code quality reviewers sequentially with re-review loops for any issues, catching both missing requirements and maintainability concerns.
  • Model selection guidance: Choose the cheapest capable model for mechanical work, upgrade for integration or architectural judgment, and escalate blocking statuses without polluting the working session.

Quick Start

Tell the controller to run Subagent-Driven Development on this plan by dispatching an implementer subagent followed by spec and code-quality reviewers for every task in this session.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I keep subagent context isolated when executing implementation plans?▼

You keep subagent context isolated by dispatching a fresh implementer subagent for each independent task, ensuring work never inherits stale history and stays focused on a single responsibility.

What is two-stage review in subagent-driven development?▼

Two-stage review runs spec compliance and code quality reviewers sequentially after each implementation, using re-review loops for any issues to catch missing requirements and maintainability concerns.

How do I automate task orchestration for independent coding tasks?▼

Automate task orchestration by dispatching fresh subagents per task within the same session, applying sequential reviews and final cross-task validation before marking completion.

Can I choose different models for implementation and code review subagents?▼

Yes, model selection guidance lets you choose the cheapest capable model for mechanical work, upgrade for integration or architectural judgment, and escalate blocking statuses without polluting the working session.

When should I use subagent-driven development for workflow automation?▼

Use subagent-driven development when tasks are largely independent within the same session and need sequential reviews before marking completion, preventing drift and rework during execution.

Related Skills

Explore More Software Engineering Skills→
makerjackiemakerjackie
1

subagent-driven-development

Dispatch fresh subagents to execute independent tasks with two-stage reviews.

Community
Advanced
danilonovaisvdanilonovaisv
1

subagent-driven-development

Dispatch isolated subagents per task and run spec-compliance and code-quality reviews.

Community
Advanced
abcnutsabcnuts
60

subagent-driven-development

Dispatch isolated subagents per task with two-stage spec and code-quality reviews.

Community
Advanced
novskidevnovskidev
2

subagent-driven-development

Dispatch fresh subagents for implementation, spec compliance review, and code quality review.

Community
Advanced