A universal template demonstrating how to structure skill instructions for cross-platform AI agents.

Install

mkdir -p .claude/skills/cm-example && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12512" && unzip -o skill.zip -d .claude/skills/cm-example && rm skill.zip

Installs to .claude/skills/cm-example

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.

A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.
104 charsno explicit “when” trigger
Beginner

Key capabilities

  • Define instructions for a universal skill format
  • Specify sub-agent tasks for platforms supporting recursive agents
  • Inject variables into the prompt context
  • Demonstrate compatibility with Antigravity, Claude, Cursor, and OpenClaw
  • Output a greeting in three different languages

How it works

The skill defines instructions and sub-agent tasks within a unified format, which an omni-agent compiles into platform-specific configurations.

Inputs & outputs

You give it
User asks for 'universal hello world'
You get back
A greeting in French, Spanish, and Japanese

When to use cm-example

  • Creating new agent skills
  • Standardizing AI assistant instructions
  • Cross-platform plugin development

About this skill

Universal Skill Example

This skill demonstrates the unified format that omni-agent will compile into platform-specific configurations.

The Instructions

When the user asks for "universal hello world", output a greeting in 3 different languages.

Sub-agent Instructions

[!NOTE] Used by platforms that support recursive agents (like Antigravity / OpenFang).

  1. Subagent A: Translate into French.
  2. Subagent B: Translate into Spanish.
  3. Subagent C: Translate into Japanese.

Context Injection

Inject these variables into the prompt context when compiling: {{ workspace_root }} {{ current_branch }}

When not to use it

  • When creating a skill not intended for the omni-agent unified format
  • When platform-specific configurations are not required

Limitations

  • The skill is a template demonstrating a format
  • It relies on an omni-agent to compile into platform-specific configurations
  • Sub-agent instructions are used by platforms that support recursive agents

How it compares

This skill provides a standard, unified format for AI agent skills, allowing for cross-platform compatibility and structured sub-agent delegation.

Compared to similar skills

cm-example side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
cm-example (this skill)03moNo flagsBeginner
skill-creator1283moReviewAdvanced
openrouter199moReviewIntermediate
skill-development179moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

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

openrouter

rawveg

OpenRouter API - Unified access to 400+ AI models through one API

19178

skill-development

anthropics

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

17145

command-development

anthropics

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

16133

agent-identifier

anthropics

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.

15122

prompt-engineering-patterns

wshobson

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

19116

Search skills

Search the agent skills registry