subagent-dev

Dispatch implementation tasks to subagents with two-stage spec and code review.

1|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/kjaylee/misskim-skills --skill subagent-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-dev
Source: https://github.com/kjaylee/misskim-skills/tree/main/skills/subagent-dev
Command: npx skills add https://github.com/kjaylee/misskim-skills --skill subagent-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the execution of complex implementation plans by delegating individual tasks to specialized subagents, ensuring each task is handled with a clean context and undergoes rigorous two-stage review.

Core Features & Use Cases

  • Task Decomposition: Breaks down multi-task plans into independent work units.
  • Subagent Dispatch: Assigns each task to a dedicated subagent for implementation.
  • Two-Stage Review: Implements a dual review process: first for spec compliance, then for code quality.
  • Enhanced ralph-loop: Strengthens the "subagent per task" principle within the ralph-loop methodology.
  • Use Case: When faced with a large feature implementation requiring multiple distinct coding steps, this skill ensures each step is coded, tested, and reviewed independently before integration, minimizing errors and maintaining code integrity.

Quick Start

Use the subagent-dev skill to execute the implementation plan for the new user authentication module.

Frequently Asked Questions about subagent-dev

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

FAQPage Schema
How do I execute complex implementation plans with independent subagents?

To execute implementation plans with subagents, this skill dispatches each work unit to a fresh subagent for coding, followed by a two-stage review process for spec compliance and code quality.

What is the two-stage review process for subagent code execution?

The two-stage review process validates subagent-generated code by first checking spec compliance, then evaluating code quality, ensuring each task unit meets requirements before integration into the ralph-loop.

How do I manage multi-task execution using the ralph-loop methodology?

You can manage multi-task execution in the ralph-loop by structuring prompts to decompose plans into independent work units, dispatching each to a fresh subagent for implementation and review.

Do I need to structure prompts carefully for subagent task management?

Yes, careful prompt structuring is required to separately define implementation, spec validation, and code quality review instructions for each subagent involved in the task execution.

When should I use a dedicated subagent for each task unit?

You should use a dedicated subagent for each task unit when handling large feature implementations requiring multiple distinct coding steps, ensuring each step is coded and reviewed independently to minimize errors.

What are the limitations of using fresh subagents for code execution?

A limitation of using fresh subagents is that each unit operates with a clean context, meaning subagents do not share execution state or memory across tasks, requiring careful prompt structuring for context.