create-subagent

Create modular subagents with YAML frontmatter and system prompt bodies.

2|Updated Apr 28, 2026
One-click install
npx skills add https://github.com/anyekoutouming/anyekoutouming --skill create-subagent-anyekoutouming
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/anyekoutouming/anyekoutouming/tree/main/create-subagent
Command: npx skills add https://github.com/anyekoutouming/anyekoutouming --skill create-subagent-anyekoutouming

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables teams to design and manage modular subagents that run specialized AI tasks in isolated contexts, simplifying governance and reuse across projects.

Core Features & Use Cases

  • YAML frontmatter-based subagent definitions (name and description) that standardize configuration and discovery.
  • System-prompt bodies that define the agent's behavior and workflow, enabling predictable delegation.
  • Project-level (.cursor/agents/) and user-level (~/.cursor/agents/) subagents with examples like code-reviewer, debugger, and data-scientist to cover common AI workflows.

Quick Start

Create a new subagent file in the appropriate directory with frontmatter and a system prompt body, then test it using the project-wide workflow.

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 in Cursor for specialized tasks?

To create AI subagents in Cursor, you define a Markdown file with YAML frontmatter specifying the name and description, followed by a system prompt body that dictates the agent's behavior, and store it in the .cursor/agents or ~/.cursor/agents directory.

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

Project-level Cursor subagents are stored in the .cursor/agents directory for project-specific workflows, while user-level subagents reside in ~/.cursor/agents to be reused globally across all your projects.

How do I configure a modular subagent system prompt for predictable delegation?

You configure a modular subagent by writing a system prompt body in a Markdown file that defines the agent's workflow and behavior, ensuring predictable delegation when the agent executes tasks in isolated contexts.

Can I include scripts and references when defining subagents in Cursor?

Yes, you can include optional directories for scripts, references, and assets alongside your Markdown subagent definition files to support deployment and governance for your AI workflows.

What are common use cases for isolated AI subagents in software engineering?

Common use cases for isolated AI subagents include standardizing workflows for code review, debugging, and data science tasks, allowing teams to run specialized AI processes with predictable behavior.

Does creating a Cursor subagent require specific dependencies or components?

Creating a Cursor subagent requires no external dependencies or components, only a Markdown file with YAML frontmatter for configuration and a system prompt body to define the agent's logic.