create-subagent

Create isolated AI subagents with customized prompts and YAML frontmatter.

1|Updated Nov 17, 2025
One-click install
npx skills add https://github.com/YanxiChen-gh/Dotfiles --skill create-subagent-yanxichen-gh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/YanxiChen-gh/Dotfiles/tree/main/cursor/skills/create-subagent
Command: npx skills add https://github.com/YanxiChen-gh/Dotfiles --skill create-subagent-yanxichen-gh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creates dedicated subagents to handle specialized AI tasks in isolated contexts, enabling reusable configurations across projects and preserving the main conversation state.

Core Features & Use Cases

  • Define project- and user-level subagents with tailored prompts for specific domains.
  • Route tasks to the appropriate subagent using clear delegation rules.
  • Share and version-control subagents to promote consistency across teams.

Quick Start

Use the create-subagent workflow to build a new subagent by following the steps outlined.

Frequently Asked Questions about create-subagent

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

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

You can create isolated AI subagents in Cursor by defining a YAML frontmatter with name and description, writing a system prompt body, and configuring optional script, reference, or asset directories to handle specialized tasks like code review or debugging.

What are project-level and user-level subagents for AI workflows?

Project-level and user-level subagents are isolated AI configurations with customized prompts. Project-level subagents are version-controlled for team consistency, while user-level subagents preserve the main conversation state across individual workflows.

How do I route tasks to the appropriate AI subagent?

You route tasks to the appropriate AI subagent by defining clear delegation rules within the subagent configuration. This isolates domain-specific contexts, such as routing debugging tasks to a debugger subagent while preserving the main conversation state.

Does this subagent management workflow require specific dependencies or components?

No specific dependencies or components are required. The subagent management workflow relies on a YAML frontmatter structure combined with a system prompt body and optional directories to build isolated AI assistants within Cursor.

Can I share and version-control AI subagents across projects?

Yes, you can share and version-control AI subagents across projects. Defining project-level subagents with tailored prompts promotes consistency across teams and enables reusable configurations for domain-specific assistants within Cursor.

When should I build isolated AI subagents instead of using the main conversation?

Build isolated AI subagents when you need dedicated assistants for specialized tasks like code reviewing or debugging. This preserves the main conversation state and enables reusable, domain-specific prompt configurations across projects.