create-subagent

Create and manage Cursor subagents with YAML frontmatter and system prompts.

1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/PandelisZ/skills --skill create-subagent-pandelisz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/PandelisZ/skills/tree/main/skills/create-subagent
Command: npx skills add https://github.com/PandelisZ/skills --skill create-subagent-pandelisz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Create custom subagents for specialized AI tasks by guiding how to structure agent prompts, scope, and deployment, enabling standardized reuse across projects.

Core Features & Use Cases

  • Define project-level (.cursor/agents/) and user-level (~/.cursor/agents/) subagents.
  • Use YAML frontmatter to define unique name and description, followed by a system prompt in the body.
  • Supports testing, iteration, and sharing via version control to align team practices.

Quick Start

Create the file at .cursor/agents/my-agent.md, add the YAML frontmatter with a unique name and description, and 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
What are AI subagents and how do they help with workflow automation?

AI subagents are specialized assistants defined by Markdown files with YAML frontmatter and system prompts, enabling consistent, reusable automation across project and user directories for standardized team workflows.

How do I create a custom AI subagent using a Markdown file?

To create a custom AI subagent, make a Markdown file at .cursor/agents/ or ~/.cursor/agents/, add YAML frontmatter with a unique name and description, and write the system prompt defining the agent's behavior in the body.

Can I share AI subagents with my team using version control?

Yes, you can share AI subagents with your team using version control by committing the project-level .cursor/agents/ directory, allowing team members to reuse, test, and iterate on standardized subagent prompts and configurations.

Does an AI subagent require YAML frontmatter to function?

Yes, YAML frontmatter is required for an AI subagent because it defines the unique name and description needed to identify and deploy the agent, while the Markdown body contains the actual system prompt guiding its specialized task.

What is the best way to organize files when defining AI subagents?

The best way to organize AI subagent files is to place the Markdown definition in .cursor/agents/ or ~/.cursor/agents/, then use optional directories like scripts/, references/, and assets/ to store supporting execution files and contextual data.

When should I use project-level versus user-level subagent directories?

Use project-level subagents in .cursor/agents/ for project-specific tasks shared via version control, and user-level subagents in ~/.cursor/agents/ for personal workflows across multiple projects to enable consistent, reusable automation.