subagent-driven-development

Automate complex workflows by dividing tasks among specialized agents with two-stage reviews.

2|Updated Jun 1, 2026
One-click install
npx skills add https://github.com/tukuyomil032/Perch --skill subagent-driven-development-tukuyomil032
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/tukuyomil032/Perch/tree/main/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/tukuyomil032/Perch --skill subagent-driven-development-tukuyomil032

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires spec-reviewer-prompt.md, implementer-prompt.md, code-quality-reviewer-prompt.md, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates complex workflows by breaking them down into isolated tasks, executing them with specialized agents, and ensuring high-quality results through two-stage reviews.

Core Features & Use Cases

  • Task Isolation: Assign tasks to specialized agents for focused execution.
  • Two-Stage Review: Ensure spec compliance and code quality with reviews.
  • Use Case: Ideal for executing detailed implementation plans, ensuring code quality in parallelized environments.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan for feature development, ensuring each task is handled by a dedicated subagent with specific review stages.

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 software development workflows with isolated tasks?

Automating complex software development workflows involves dividing tasks to specialized agents for focused execution. This approach ensures task isolation and handles parallel execution effectively.

How does the two-stage code review process work for implementation plans?

The two-stage code review process works by evaluating spec compliance first, then assessing code quality. Review templates guide each stage to ensure high-quality code execution and adherence to plans.

What is the best way to ensure spec compliance when executing parallel development tasks?

Ensuring spec compliance during parallel development tasks requires specialized agents and structured review templates. This workflow automation verifies that isolated tasks meet the original implementation plan.

Do I need a detailed implementation plan before starting subagent-driven development?

Yes, a detailed implementation plan is required before starting. You also need specialized agents for task delegation and specific review templates to execute the two-stage review process.

When should I use task isolation for workflow automation in software engineering?

Use task isolation for workflow automation when executing detailed implementation plans in parallelized environments. It ensures high-quality results by assigning focused tasks to dedicated subagents.

Why use specialized agents for code reviews instead of a single automated pass?

Using specialized agents separates spec compliance checks from code quality reviews. This two-stage review mechanism prevents bottlenecks and ensures thorough validation against the implementation plan.