create-skill

name	create-skill
description	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.

Skill Creator

This skill provides guidance for creating effective skills.

About Skills

Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

What Skills Provide

1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks

Anatomy of a Skill

Every skill consists of a required SKILL.md file and optional bundled resources:

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   ├── description: (required)
│   │   └── allowed-tools: (optional)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

SKILL.md (required)

Metadata Quality: The name and description in YAML frontmatter determine when Claude will use the skill. Be specific about what the skill does and when to use it. Use third-person form (e.g., "This skill should be used when..." instead of "Use this skill when...").

allowed-tools (optional): Restricts which tools Claude can use within the skill. Leave empty to allow all tools (recommended unless restriction is needed).

Bundled Resources (optional)

Scripts (scripts/)

Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.

• When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed
• Example: scripts/rotate_pdf.py for PDF rotation tasks
• Benefits: Token efficient, deterministic, may be executed without loading into context
• Note: Scripts may still need to be read by Claude for patching or environment-specific adjustments

References (references/)

Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.

• When to include: For documentation that Claude should reference while working
• Examples: references/finance.md for financial schemas, references/api_docs.md for API specifications, references/policies.md for company policies
• Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
• Benefits: Keeps SKILL.md lean, loaded only when Claude determines it's needed
• Best practice: If files are large (>10k words), include grep search patterns in SKILL.md
• Avoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.

Assets (assets/)

Files not intended to be loaded into context, but rather used within the output Claude produces.

• When to include: When the skill needs files that will be used in the final output
• Examples: assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate
• Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
• Benefits: Separates output resources from documentation, enables Claude to use files without loading them into context

Progressive Disclosure Design Principle

Skills use a three-level loading system to manage context efficiently:

1. Metadata (name + description) - Always in context (~100 words)
2. SKILL.md body - When skill triggers (<5k words)
3. Bundled resources - As needed by Claude (Unlimited*)

*Unlimited because scripts can be executed without reading into context window.

Tool Restrictions with allowed-tools

The allowed-tools field restricts which tools Claude can use within the skill. Available tools include:

File Operations:

• Read - Read file contents
• Write - Create new files
• Edit - Modify existing files
• Glob - Find files by pattern (e.g., "**/*.js")
• Grep - Search file contents with regex

Execution:

• Bash - Run shell commands
• BashOutput - Get output from background shells
• KillShell - Terminate background shells

Web & Search:

• WebFetch - Fetch and analyze web content
• WebSearch - Search the web for information

Specialized:

• Task - Launch specialized sub-agents
• NotebookEdit - Edit Jupyter notebooks
• TodoWrite - Manage task lists
• AskUserQuestion - Ask the user questions during execution
• Skill - Invoke other skills
• SlashCommand - Execute slash commands
• ExitPlanMode - Exit planning mode

Example: allowed-tools: Read, Grep, Glob (for read-only code analysis)

Important Notes:

• Tool restrictions work at the tool level, not command level. You cannot restrict Bash to only specific commands (e.g., can't do Bash(git))
• If you need to limit bash usage, rely on clear instructions in the skill rather than tool restrictions
• Leave allowed-tools empty to allow all tools (recommended unless restriction is needed)

Skill Creation Process

To create a skill, follow the "Skill Creation Process" in order, skipping steps only if there is a clear reason why they are not applicable.

Step 1: Understanding the Skill with Concrete Examples

Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.

To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.

For example, when building an image-editor skill, relevant questions include:

• "What functionality should the image-editor skill support? Editing, rotating, anything else?"
• "Can you give some examples of how this skill would be used?"
• "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
• "What would a user say that should trigger this skill?"

To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.

Conclude this step when there is a clear sense of the functionality the skill should support.

Step 2: Planning the Reusable Skill Contents

To turn concrete examples into an effective skill, analyze each example by:

1. Considering how to execute on the example from scratch
2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly

Example: When building a pdf-editor skill to handle queries like "Help me rotate this PDF," the analysis shows:

1. Rotating a PDF requires re-writing the same code each time
2. A scripts/rotate_pdf.py script would be helpful to store in the skill

Example: When designing a frontend-webapp-builder skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:

1. Writing a frontend webapp requires the same boilerplate HTML/React each time
2. An assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skill

Example: When building a big-query skill to handle queries like "How many users have logged in today?" the analysis shows:

1. Querying BigQuery requires re-discovering the table schemas and relationships each time
2. A references/schema.md file documenting the table schemas would be helpful to store in the skill

To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.

Step 3: Initializing the Skill

At this point, it is time to actually create the skill.

Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.

Choose a Name

• Use lowercase letters, numbers, and hyphens only
• Maximum 64 characters
• Make it descriptive and specific (e.g., "analyze-excel", "review-security", "generate-docs")
• Ask the user if unsure about the name

Create Directory Structure

mkdir -p skills/skill-name/{scripts,references,assets}

Or manually create:

skills/skill-name/
├── SKILL.md (required)
├── scripts/ (optional)
├── references/ (optional)
└── assets/ (optional)

Choose Storage Location

• Project skills: .claude/skills/skill-name/ or skills/skill-name/ (shared via git)
• Personal skills: ~/.claude/skills/skill-name/ (user-specific)

Step 4: Edit the Skill

When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Focus on including information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.

Start with Reusable Skill Contents

To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.

Also, delete any example files and directories not needed for the skill.

Update SKILL.md

Writing Style: Write the entire skill using imperative/infinitive form (verb-first instructions), not second person. Use objective, instructional language (e.g., "To accomplish X, do Y" rather than "You should do X" or "If you need to do X"). This maintains consistency and clarity for AI consumption.

Required Frontmatter:

---
name: skill-name
description: This skill should be used when... [Be specific about what it does and when to use it]
allowed-tools: Tool1, Tool2 (optional - leave empty to allow all tools)
---

SKILL.md Content: To complete SKILL.md, answer the following questions:

1. What is the purpose of the skill, in a few sentences?
2. When should the skill be used?
3. In practice, how should Claude use the skill? All reusable skill contents developed above should be referenced so that Claude knows how to use them.

Best Practices:

• Keep skills focused on ONE capability
• Use clear, actionable instructions
• Include examples where helpful
• Avoid duplication between SKILL.md and references/ files
• Keep SKILL.md lean (<5k words) by moving detailed information to references/
• If references/ files are large (>10k words), include grep search patterns in SKILL.md

Step 5: Test and Iterate

After creating the skill, test it on real tasks:

1. Use the skill - Try it on concrete examples from Step 1
2. Notice struggles - Identify where Claude struggles or is inefficient
3. Identify improvements - Determine how SKILL.md or bundled resources should be updated
4. Implement changes - Update the skill based on learnings
5. Test again - Repeat the cycle

Iteration workflow:

• Fresh context from recent usage is the best time to improve
• Update instructions, add missing references, refine scripts
• Consider whether information should move between SKILL.md and references/

Step 6: Package and Distribute (Optional)

For sharing skills with others:

1. Create a distributable package:

   • Zip the entire skill directory
   • Name it after the skill (e.g., my-skill.zip)
   • Include all files: SKILL.md, scripts/, references/, assets/

2. Validate before sharing:

   • YAML frontmatter is properly formatted
   • Required fields (name, description) are present
   • Directory structure follows conventions
   • File references in SKILL.md are correct

3. Distribution:

   • Share zip file directly
   • Or commit to version control (for project skills)

Skill vs Slash Command

Skills are model-invoked (Claude decides when to use them based on context). Slash commands are user-invoked (user explicitly runs them with /command).

Choose skills for capabilities users might forget to invoke explicitly. Choose slash commands for specific workflows users want to control.

Summary

Key Principles:

1. Start with concrete examples
2. Identify reusable resources (scripts/references/assets)
3. Use progressive disclosure (lean SKILL.md, detailed references/)
4. Write in imperative/infinitive form
5. Test and iterate on real usage
6. Keep skills focused on one capability

Directory Structure:

• SKILL.md - Core instructions (<5k words)
• scripts/ - Executable code for deterministic tasks
• references/ - Documentation loaded as needed
• assets/ - Files used in output