AG

agent-identifier

Provides a framework for creating autonomous subagents with custom system prompts, tools, and YAML frontmatter.

Install

mkdir -p .claude/skills/agent-identifier && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/40" && unzip -o skill.zip -d .claude/skills/agent-identifier && rm skill.zip

Installs to .claude/skills/agent-identifier

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
357 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • →Define autonomous agent structure
  • →Configure YAML frontmatter for agents
  • →Design system prompts for subagents
  • →Set agent triggering conditions with examples
  • →Manage agent tool access and models

How it works

It uses a standardized markdown format with YAML frontmatter to define agent behavior, triggering logic, and system prompts for autonomous execution.

Inputs & outputs

You give it
Agent purpose and requirements
You get back
Agent configuration file in markdown

When to use agent-identifier

  • →Create a new subagent
  • →Define agent system prompts
  • →Configure agent triggering conditions
  • →Standardize agent tool access

About agent-identifier

This skill defines the structure and best practices for creating autonomous agents. It ensures correct use of YAML frontmatter, naming conventions, and system prompt design to maintain consistency across Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

When not to use it

  • →When the task is a simple user-initiated command
  • →When the agent does not require autonomy

Prerequisites

Claude Code plugin environment

Limitations

  • →Requires adherence to specific naming and formatting rules
  • →Triggering logic relies on accurate description examples

How it compares

It provides a strict framework for autonomous agent development, ensuring consistency across plugins compared to ad-hoc agent creation.

Compared to similar skills

agent-identifier side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
agent-identifier (this skill)151yReviewIntermediate
skill-creator1287moReviewAdvanced
skill-development171yReviewIntermediate
llama-factory151yNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by anthropics

View all by anthropics →

frontend-design

anthropics

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

481544

pptx

anthropics

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

393763

webapp-testing

anthropics

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

353585

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

skill-creator

anthropics

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

128200

docx

anthropics

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

93225

You might also like

Search skills

Search the agent skills registry