create-subagent

Create and deploy custom subagents for specialized tasks with Markdown system prompts.

1|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/janjaszczak/cursor --skill create-subagent-janjaszczak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/janjaszczak/cursor/tree/main/skills-cursor/create-subagent
Command: npx skills add https://github.com/janjaszczak/cursor --skill create-subagent-janjaszczak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagents enable you to isolate specialized AI tasks in separate, reusable agents with dedicated prompts, improving modularity and cross-project consistency.

Core Features & Use Cases

  • Frontmatter-driven identity: Each subagent is defined by a YAML frontmatter containing a unique name and description, and stores its system prompt in the Markdown body.
  • Location-based scoping: Supports project-level subagents under .cursor/agents/ and user-level subagents under ~/.cursor/agents/ for personal reuse.
  • Extensible formats: Works with a Markdown file per subagent and can be extended with example configurations for common tasks (e.g., code review, debugging, data processing).
  • Version control friendly: Subagents can be checked into version control to share with teams.
  • Testable and reusable: Designed to be easily tested and reused across workflows.

Quick Start

Create a new subagent by placing a Markdown file with a frontmatter name and description in the appropriate agents directory 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
How do I create custom subagents in Cursor for specialized tasks?

To create custom subagents in Cursor, place a Markdown file with YAML frontmatter containing a unique name and description in your agents directory, then write the system prompt in the Markdown body.

What is the difference between project-level and user-level subagents?

Project-level subagents are stored under .cursor/agents/ for team-specific workflows, while user-level subagents reside in ~/.cursor/agents/ for personal reuse across all your projects.

Can I check in custom subagents to version control for team sharing?

Yes, subagents are version control friendly because they are defined as standard Markdown files. You can check them into your repository to share specialized AI workflows with your team.

What format does a subagent file need to follow?

A subagent file must use a Markdown format with a YAML frontmatter block defining the agent's name and description, followed by the main body which serves as the system prompt.

What are common use cases for delegating tasks to subagents?

Subagents are commonly used for code review, debugging, data processing, and domain-specific automation, allowing you to isolate specialized AI tasks into reusable, modular components.

Do I need any dependencies to set up subagent workflows?

No external dependencies are required to set up subagent workflows. You only need the Cursor environment and correctly formatted Markdown files to deploy your specialized agents.