skills.rest
RedWoodOG
RedWoodOGCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Automate multi-task implementation plans with isolated subagents and two-stage reviews.

174|23|Updated Apr 3, 2026
Search Tags:#automation#workflow#planning#subagents#delegation#code-review
One-click install
npx skills add https://github.com/RedWoodOG/Hermes-Desktop --skill subagent-driven-development-redwoodog
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/RedWoodOG/Hermes-Desktop/tree/main/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/RedWoodOG/Hermes-Desktop --skill subagent-driven-development-redwoodog

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fresh, structured implementation plans often stall when tasks are interdependent yet require isolated execution and rigorous reviews. This skill solves that by dispatching a new subagent for every task and enforcing a two-stage review process (spec compliance followed by code quality).

Core Features & Use Cases

  • Fresh subagent per task ensures clean context and reduces cross-task contamination.
  • Two-stage reviews catch spec gaps and quality issues early, increasing reliability.
  • End-to-end workflow from plan parsing to task execution and final integration review.

Quick Start

Provide a plan and run the first task through the subagent-driven workflow.

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-task implementation plans with isolated execution?▼

Automating multi-task implementation plans involves dispatching a new subagent for every task to ensure clean context, followed by enforcing a two-stage review for spec compliance and code quality.

What is the best way to prevent cross-task context contamination during code generation?▼

Preventing cross-task context contamination requires assigning fresh subagents per task, which isolates execution environments and reduces cross-contamination during complex parallelizable workflows.

How does two-stage code review work for spec compliance and quality?▼

Two-stage code review works by first checking spec compliance to catch gaps early, followed by a code quality review, concluding with a final integration review to mark overall completion.

Can I use subagent delegation for complex plans with parallelizable tasks?▼

Yes, subagent delegation is specifically designed for complex plans with parallelizable tasks where strict spec compliance and code quality are critical, supporting end-to-end workflow from plan parsing to execution.

When should I avoid using fresh subagents for task delegation?▼

You should avoid using fresh subagents for task delegation when implementation plans lack parallelizable tasks or when strict spec compliance and rigorous code quality reviews are not required for the workflow.

Related Skills

Explore More Software Engineering Skills→
databrickslabsdatabrickslabs
38

subagent-driven-development

Execute multi-task implementation plans with fresh subagents and two-stage reviews.

Official
Advanced
lagz0nelagz0ne
2

subagent-driven-development

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

Community
Advanced
ToqsickToqsick

subagent-driven-development

Orchestrate subagent execution with a two-stage review for spec compliance and code quality.

Community
Advanced
fefogarciafefogarcia
1

multi-agent-patterns

Design and implement multi-agent architectures with supervisor, peer-to-peer, and hierarchical patterns.

Community
Advanced