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

Core Principles

Concise is Key

The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills’ metadata, and the actual user request.

Default assumption: Claude is already very smart. Only add context Claude doesn’t already have. Challenge each piece of information: “Does Claude really need this explanation?” and “Does this paragraph justify its token cost?”

Prefer concise examples over verbose explanations.

Set Appropriate Degrees of Freedom

Match the level of specificity to the task’s fragility and variability:

High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.

Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.

Low freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.

Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

Composability

Skills should be modular and narrowly scoped. Each skill should do one thing well:

• One concern per skill: A PDF skill processes PDFs; a charting skill creates charts. Avoid “Swiss army knife” skills.
• Scoped descriptions: Narrow descriptions prevent unintended triggering and make skills composable — users can combine multiple focused skills rather than relying on one monolithic skill.
• Design for combination: When skills may work together, use consistent terminology and compatible output formats so one skill’s output can feed into another.

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)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

SKILL.md (required)

Every SKILL.md consists of:

• Frontmatter (YAML): Contains name and description fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
• Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).

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
• 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.

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
• Benefits: Separates output resources from documentation, enables Claude to use files without loading them into context

What to Not Include in a Skill

A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files (README.md, INSTALLATION_GUIDE.md, CHANGELOG.md, etc.). The skill should only contain the information needed for an AI agent to do the job at hand.

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 because scripts can be executed without reading into context window)

Progressive Disclosure Patterns

Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them.

Key principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details into separate reference files.

Pattern 1: High-level guide with references

# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]

## Advanced features

- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns

Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.

Pattern 2: Domain-specific organization

For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:

bigquery-skill/
├── SKILL.md (overview and navigation)
└── reference/
    ├── finance.md (revenue, billing metrics)
    ├── sales.md (opportunities, pipeline)
    └── marketing.md (campaigns, attribution)

Pattern 3: Conditional details

Show basic content, link to advanced content:

## Creating documents

Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).

## Editing documents

For simple edits, modify the XML directly.

**For tracked changes**: See [REDLINING.md](REDLINING.md)
**For OOXML details**: See [OOXML.md](OOXML.md)

Important guidelines:

• Avoid deeply nested references – Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
• Structure longer reference files – For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing.

Reference Materials

Consult these references based on your needs during skill creation:

• references/skill-specification.md — Read when you need to verify frontmatter field constraints, naming rules, directory structure requirements, or validation rules for SKILL.md format compliance.
• references/authoring-best-practices.md — Read when writing or reviewing skill content for quality: effective descriptions, naming conventions, testing strategies, anti-patterns, evaluation-driven development, and the complete skill quality checklist.
• references/workflows.md — Read when designing multi-step processes: sequential, conditional, iterative, and multi-MCP workflow patterns.
• references/output-patterns.md — Read when the skill needs to produce consistent output formats: template and example patterns.
• references/testing-and-debugging.md — Read when testing a skill or debugging triggering, execution, or quality problems.
• references/skill-categories.md — Read when choosing a skill archetype: document/asset creation, workflow automation, or MCP enhancement.
• references/distribution-guide.md — Read when preparing a skill for distribution: channels, packaging formats, and positioning.

Skill Creation Process

Skill creation involves these steps:

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Validate and package the skill
6. Iterate based on real usage

Follow these steps in order, skipping 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?”
• “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.

Before moving on, also define success criteria:

• Trigger queries: What should a user say to activate this skill? List 3-5 example queries.
• Output quality: What does a good result look like? Define the minimum acceptable output.

Conclude this step when there is a clear sense of the functionality the skill should support and how success will be measured.

Step 2: Planning the Reusable Skill Contents

First, identify which category the skill falls into — Document & Asset Creation, Workflow Automation, or MCP Enhancement. Each category has distinct design implications. See references/skill-categories.md for guidance.

Then, turn concrete examples into an effective skill by analyzing each example:

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, the analysis shows:

1. Writing a frontend webapp requires the same boilerplate each time
2. An assets/hello-world/ template 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.

When creating a new skill from scratch, always run the init_skill.py script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires.

Usage:

scripts/init_skill.py <skill-name> --path <output-directory>

The script:

• Creates the skill directory at the specified path
• Generates a SKILL.md template with proper frontmatter and TODO placeholders
• Creates example resource directories: scripts/, references/, and assets/
• Adds example files in each directory that can be customized or deleted

After initialization, customize or remove the generated SKILL.md and example files as needed.

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. Include information that would be beneficial and non-obvious to Claude.

Learn Proven Design Patterns

Consult these helpful guides based on your skill’s needs:

• Multi-step processes: See references/workflows.md for sequential workflows and conditional logic
• Specific output formats or quality standards: See references/output-patterns.md for template and example patterns

These files contain established best practices for effective skill design.

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.

Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected.

Any example files and directories not needed for the skill should be deleted.

Update SKILL.md

Writing Guidelines: Always use imperative/infinitive form.

Frontmatter

Write the YAML frontmatter with name and description:

• name: The skill name (hyphen-case, max 64 characters, lowercase letters/digits/hyphens only)
• description: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.
  • Include both what the Skill does and specific triggers/contexts for when to use it.
  • Include all “when to use” information here – Not in the body. The body is only loaded after triggering.

Do not include any other fields in YAML frontmatter unless specifically needed (allowed-tools, license, compatibility, metadata are optional).

Body

Write instructions for using the skill and its bundled resources.

Step 5: Validate and Package

Once development of the skill is complete, validate and package it for distribution.

Validation

Primary (recommended): Use skills-ref validate for authoritative validation against the official Agent Skills specification:

skills-ref validate <path/to/skill-folder>

If skills-ref is not installed, install it from the git submodule:

uv pip install -e deps/agentskills/skills-ref/

Fallback: Use scripts/quick_validate.py for lightweight validation (requires only PyYAML):

python3 scripts/quick_validate.py <path/to/skill-folder>

Packaging

Package the validated skill into a distributable .skill file:

scripts/package_skill.py <path/to/skill-folder>

Optional output directory:

scripts/package_skill.py <path/to/skill-folder> ./dist

The packaging script will:

1. Validate the skill automatically (using quick_validate.py)
2. Package the skill if validation passes, creating a .skill file that includes all files and maintains the proper directory structure for distribution.

If validation fails, fix any errors and run the packaging command again.

Step 6: Iterate

Before considering the skill complete, test across three areas:

1. Triggering: Verify the skill activates on 5+ paraphrased queries and does NOT activate on 3+ unrelated queries
2. Functionality: Run the primary workflow end-to-end with realistic inputs; test at least one edge case
3. Performance: Compare output quality with and without the skill on representative tasks

See references/testing-and-debugging.md for detailed testing methodology and common debugging solutions.

After testing, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.

Iteration workflow:

1. Use the skill on real tasks
2. Notice struggles or inefficiencies (see iteration signals in references/testing-and-debugging.md)
3. Identify how SKILL.md or bundled resources should be updated
4. Implement changes and test again