skills.rest
GOODWORKRINKZ
GOODWORKRINKZCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

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

Updated Mar 23, 2026
Search Tags:#automation#workflow#planning#development#subagents#two-stage-review#ai-prompting
One-click install
npx skills add https://github.com/GOODWORKRINKZ/mylamp --skill subagent-driven-development-goodworkrinkz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/GOODWORKRINKZ/mylamp/tree/main/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/GOODWORKRINKZ/mylamp --skill subagent-driven-development-goodworkrinkz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development helps teams execute complex plans by dispatching fresh subagents per task within the same session, enabling rapid iteration while preserving isolation.

Core Features & Use Cases

  • Fresh subagents per task with two-stage reviews after each task (spec compliance first, then code quality)
  • In-session task extraction and parallel/serial task handling for efficient planning
  • Automatic re-review loops to ensure fixes until criteria are met
  • Real-world use: breaking down a multi-step plan into independent tasks and verifying each through dedicated reviewers

Quick Start

Dispatch a plan runner that creates per-task subagents and routes them through spec and quality reviews.

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 complex development plans with isolated context per task?▼

Automate complex development plans by dispatching fresh subagents for each task within a session, which enables rapid iteration while preserving isolated context to prevent interference.

What is a two-stage review workflow for subagent-driven development?▼

A two-stage review workflow evaluates subagent output by first checking spec compliance, then assessing code quality, running automatic re-review loops until all criteria are met before merging.

How do I break down a multi-step implementation plan into independent tasks?▼

Break down multi-step plans using an in-session task extraction workflow that identifies mostly independent tasks, allowing you to handle them in parallel or serial for efficient planning.

Can I run spec compliance and code quality checks sequentially for AI-generated code?▼

Yes, you can run checks sequentially by routing AI-generated code through dedicated spec and code quality reviewer prompts, ensuring automatic re-review loops trigger fixes until criteria are satisfied.

Does subagent-driven development require external dependencies to orchestrate tasks?▼

No, subagent-driven development requires no external dependencies, using only internal implementer, spec-reviewer, and code-quality-reviewer prompts to orchestrate tasks and structured reviews.

When should I avoid using fresh subagents per task in my workflow?▼

Avoid using fresh subagents per task when your implementation plan contains tightly coupled tasks, as this approach relies on tasks being mostly independent within the current session for isolated context.

Related Skills

Explore More Software Engineering Skills→
LordkaitoLordkaito

subagent-driven-development

Dispatch subagents to execute implementation tasks with two-stage reviews.

Community
Advanced
HankLiu447HankLiu447
3

code-review

Automate two-stage code reviews for specification compliance and code quality.

Community
Intermediate
evanfang0054evanfang0054

subagent-driven-development

Dispatch subagents to execute development tasks with automated reviews.

Community
Advanced
blueskies1818blueskies1818
1

subagent-driven-development

Orchestrate subagents to implement tasks and review spec compliance and code quality.

Community
Advanced