skills.rest
rkz91
rkz91COMMUNITY
Explore all skills by this author →
GitHub

create-subagent

Automate creation and management of Cursor subagents with YAML frontmatter and structured bodies.

264|11|Updated Apr 25, 2026
Search Tags:#automation#devops#templates#subagents#prompts#cursor#agent-management
One-click install
npx skills add https://github.com/rkz91/coco --skill create-subagent-rkz91
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/rkz91/coco/tree/main/adapters/cursor/skills/create-subagent
Command: npx skills add https://github.com/rkz91/coco --skill create-subagent-rkz91

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to rapidly define, store, and reuse specialized AI subagents within Cursor, eliminating boilerplate setup and promoting consistency.

Core Features & Use Cases

  • Define a new subagent with a YAML frontmatter containing a unique name and a clear description
  • Persist the system prompt in the body to control behavior, scope, and delegation rules
  • Support project-level and user-level subagents stored under .cursor/agents/ and ~/.cursor/agents/
  • Facilitate reuse and version control by checking subagents into code repositories

Quick Start

Create a new subagent file at .cursor/agents/my-agent.md with frontmatter for name and description, then write the system prompt in the body.

Frequently Asked Questions about create-subagent

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

FAQPage Schema
How do I create specialized AI subagents in Cursor for specific coding tasks?▼

You can create specialized AI subagents in Cursor by defining a Markdown file with YAML frontmatter containing a unique name and description, followed by a structured body that hosts the system prompt to control behavior and delegation rules.

What is the best way to manage reusable AI agent prompts across a development team?▼

Managing reusable AI agent prompts across a team is best achieved by defining subagents with structured frontmatter and checking these files into your code repository, enabling version control and consistent reuse across the codebase.

Where should I store project-level subagents versus user-level subagents in Cursor?▼

Project-level subagents should be stored under the .cursor/agents/ directory for codebase-specific tasks, while user-level subagents are stored in the ~/.cursor/agents/ directory for broader, cross-project workflows.

Can I include external scripts and reference files when building a Cursor agent?▼

Yes, you can include external scripts, references, and assets to support advanced workflows by specifying optional directories alongside your subagent file to host supplementary execution materials.

What frontmatter fields are required to define a new subagent in a Cursor workflow?▼

Defining a new subagent requires YAML frontmatter with at least a name and description field to establish the agent's identity, while the body of the file persists the system prompt controlling its scope.

How does version control work for AI agent management in collaborative environments?▼

Version control for AI agent management works by storing your subagent definitions as Markdown files within your project repository, allowing teams to track prompt changes and maintain consistency through standard Git workflows.

Related Skills

Explore More Software Engineering Skills→
gongzeqgongzeq

trellis-meta

Explain and customize local Trellis architecture files in user projects.

Community
Intermediate
shankurshankur

create-subagent

Create custom subagents in Cursor with custom prompts and system instructions.

Community
Intermediate
refly-airefly-ai
199

github

Manage GitHub repositories, issues, and pull requests programmatically.

Official
Intermediate
victorjoshi9victorjoshi9
1

agent-development

Create Claude Code agent files with YAML frontmatter and validation scripts.

Community
Advanced