example-skill
A standard template and reference for developers building new skills for AI agents.
Install
mkdir -p .claude/skills/example-skill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/971" && unzip -o skill.zip -d .claude/skills/example-skill && rm skill.zipInstalls to .claude/skills/example-skill
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 "demonstrate skills", "show skill format", "create a skill template", or discusses skill development patterns. Provides a reference template for creating Claude Code plugin skills.Key capabilities
- →Demonstrate the required file structure for Claude Code plugin skills.
- →Explain the purpose and usage of required and optional supporting files.
- →Detail the supported frontmatter options like name, description, and version.
- →Provide guidelines for writing effective skill descriptions.
- →Outline content guidelines for clear purpose, structured guidance, and actionable instructions.
- →Suggest best practices for skill development, such as focus and clear activation conditions.
How it works
The skill provides a reference template and guidelines for creating Claude Code plugin skills, detailing file structure, frontmatter options, and content best practices.
Inputs & outputs
When to use example-skill
- →Creating a new skill file
- →Understanding skill development patterns
- →Validating skill documentation format
About this skill
Example Skill
This skill demonstrates the structure and format for Claude Code plugin skills.
Overview
Skills are model-invoked capabilities that Claude autonomously uses based on task context. Unlike commands (user-invoked) or agents (spawned by Claude), skills provide contextual guidance that Claude incorporates into its responses.
When This Skill Applies
This skill activates when the user's request involves:
- Creating or understanding plugin skills
- Skill template or reference needs
- Skill development patterns
Skill Structure
Required Files
skills/
└── skill-name/
└── SKILL.md # Main skill definition (required)
Optional Supporting Files
skills/
└── skill-name/
├── SKILL.md # Main skill definition
├── README.md # Additional documentation
├── references/ # Reference materials
│ └── patterns.md
├── examples/ # Example files
│ └── sample.md
└── scripts/ # Helper scripts
└── helper.sh
Frontmatter Options
Skills support these frontmatter fields:
- name (required): Skill identifier
- description (required): Trigger conditions - describe when Claude should use this skill
- version (optional): Semantic version number
- license (optional): License information or reference
Writing Effective Descriptions
The description field is crucial - it tells Claude when to invoke the skill.
Good description patterns:
description: This skill should be used when the user asks to "specific phrase", "another phrase", mentions "keyword", or discusses topic-area.
Include:
- Specific trigger phrases users might say
- Keywords that indicate relevance
- Topic areas the skill covers
Skill Content Guidelines
- Clear purpose: State what the skill helps with
- When to use: Define activation conditions
- Structured guidance: Organize information logically
- Actionable instructions: Provide concrete steps
- Examples: Include practical examples when helpful
Best Practices
- Keep skills focused on a single domain
- Write descriptions that clearly indicate when to activate
- Include reference materials in subdirectories for complex skills
- Test that the skill activates for expected queries
- Avoid overlap with other skills' trigger conditions
How it compares
This skill offers a specific template and structured guidance for developing Claude Code plugin skills, which differs from general programming advice.
Compared to similar skills
example-skill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| example-skill (this skill) | 3 | 8mo | No flags | Beginner |
| command-development | 16 | 8mo | Review | Intermediate |
| prpm-development | 6 | 8mo | Review | Intermediate |
| rule-identifier | 5 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by anthropics
View all by anthropics →You might also like
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.
prpm-development
pr-pm
Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment
rule-identifier
anthropics
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
autonomous-agent-patterns
davila7
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
command-creator
davila7
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
agent-orchestration-improve-agent
sickn33
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.