skills.rest
cuongnm-dev
cuongnm-devCOMMUNITY
Explore all skills by this author →
GitHub

create-subagent

Create custom AI subagents with YAML frontmatter and markdown system prompts.

Updated Aug 27, 2026
Search Tags:#subagents#workflow-automation#prompt-engineering#ai-agents#system-prompts#modular-ai
One-click install
npx skills add https://github.com/cuongnm-dev/team-ai-config --skill create-subagent-cuongnm-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-subagent
Source: https://github.com/cuongnm-dev/team-ai-config/tree/main/cursor/skills-cursor/create-subagent
Command: npx skills add https://github.com/cuongnm-dev/team-ai-config --skill create-subagent-cuongnm-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables teams to create and reuse custom AI subagents. Subagents are isolated context assistants with tailored system prompts, allowing specialized workflows and modular AI capabilities across projects.

Core Features & Use Cases

  • Isolated contexts: Build subagents with focused prompts to handle domain-specific tasks (e.g., code reviews, debugging, content moderation).
  • Team-wide reuse: Check into version control to share subagents across projects and teams.
  • Flexible formats: Define subagents with YAML frontmatter (name, description) and a body that serves as the system prompt.

Quick Start

Create a new subagent file in the appropriate location and define its frontmatter and system prompt.

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 like code reviews and debugging?▼

To create AI subagents, you define a file with YAML frontmatter specifying the name and description, and use the markdown body as the system prompt to handle specialized workflows like code reviews and debugging.

What are isolated context subagents and how do they work for modular AI workflows?▼

Isolated context subagents are custom AI assistants with tailored system prompts that execute domain-specific tasks independently. They work by using a defined markdown body as the system prompt for focused, modular execution.

Can I share custom AI subagents across projects and teams?▼

Yes, you can share custom AI subagents across projects and teams by checking the subagent files into version control, enabling team-wide reuse of specialized workflows and domain-specific assistants.

What is the correct format for defining custom AI subagents?▼

The correct format for defining custom AI subagents uses YAML frontmatter to specify the name and description, while the markdown body of the file serves as the system prompt for execution.

Do I need any dependencies to set up project-level or user-level subagents?▼

No dependencies are required to set up project-level or user-level subagents. You only need to create a new subagent file in the appropriate location and define its YAML frontmatter and system prompt.

Related Skills

Explore More Software Engineering Skills→
outfitter-devoutfitter-dev
28

subagent-authoring

Create or update Claude Code subagents with YAML frontmatter and system prompts.

Official
Advanced
zangjeicyzangjeicy

subagent-driven-development

Dispatch specialized subagents for task execution and two-stage quality reviews.

Community
Advanced
ccfccf

architecture-decision-records

Document architectural decisions with a MADR-style template and lifecycle.

Community
Advanced
shankurshankur

create-subagent

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

Community
Intermediate