Skills Creator

Goal: Create well-structured Agent Skills following best practices for discoverability, conciseness, and progressive disclosure.

IMPORTANT: Skills configuration should be concise and high-level. Only include context Claude does not already know.

Workflow

1. Read references: skills-docs.md and best-practices.md in .claude/skills/skills-creator/references/ 2. Analyze requirements and determine freedom level 3. Create SKILL.md using template from .claude/skills/skills-creator/templates/template.md 4. Add resources(reference files, scripts, etc.) alongside the SKILL.md file only if necessary. Use folder to organize resources. 5. Save to .claude/skills/[skill-name]/SKILL.md and report completion

Rules

• Only add context Claude doesn't already know
• Keep references one level deep from SKILL.md
• Provide one default approach, avoid offering multiple options
• Use forward slashes in file paths (no Windows-style paths)
• Match freedom level to task fragility (high freedom for flexible tasks, low for critical operations)

Acceptance Criteria

• Skill saved to .claude/skills/[skill-name]/SKILL.md
• Name valid (max 64 chars, lowercase letters/numbers/hyphens only)
• Description valid (max 1024 chars, third person, no "I" or "you")
• Description includes what skill does AND when to use it
• SKILL.md body under 500 lines
• Consistent terminology throughout
• No duplicate or conflicting skills exist
• No time-sensitive information included
• Name defined using gerund form (e.g., processing-pdfs, analyzing-data)

Skill authoring best practices

Learn how to write effective Skills that Claude can discover and use successfully.

---

Good Skills are concise, well-structured, and tested with real usage. This guide provides practical authoring decisions to help you write Skills that Claude can discover and use effectively.

For conceptual background on how Skills work, see the Skills overview.

Core principles

Concise is key

The context window is a public good. Your Skill shares the context window with everything else Claude needs to know, including:

• The system prompt
• Conversation history
• Other Skills' metadata
• Your actual request

Not every token in your Skill has an immediate cost. At startup, only the metadata (name and description) from all Skills is pre-loaded. Claude reads SKILL.md only when the Skill becomes relevant, and reads additional files only as needed. However, being concise in SKILL.md still matters: once Claude loads it, every token competes with conversation history and other context.

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?"
• "Can I assume Claude knows this?"
• "Does this paragraph justify its token cost?"

Good example: Concise (approximately 50 tokens):

````markdown

Extract PDF text

Use pdfplumber for text extraction:

import pdfplumber

with pdfplumber.open("file.pdf") as pdf:
    text = pdf.pages[0].extract_text()

````

Bad example: Too verbose (approximately 150 tokens):

## Extract PDF text

PDF (Portable Document Format) files are a common file format that contains
text, images, and other content. To extract text from a PDF, you'll need to
use a library. There are many libraries available for PDF processing, but we
recommend pdfplumber because it's easy to use and handles most cases well.
First, you'll need to install it using pip. Then you can use the code below...

The concise version assumes Claude knows what PDFs are and how libraries work.

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
• Heuristics guide the approach

Example:

## Code review process

1. Analyze the code structure and organization
2. Check for potential bugs or edge cases
3. Suggest improvements for readability and maintainability
4. Verify adherence to project conventions

Medium freedom (pseudocode or scripts with parameters):

Use when:

• A preferred pattern exists
• Some variation is acceptable
• Configuration affects behavior

Example:

````markdown

Generate report

Use this template and customize as needed:

def generate_report(data, format="markdown", include_charts=True):
    # Process data
    # Generate output in specified format
    # Optionally include visualizations

````

Low freedom (specific scripts, few or no parameters):

Use when:

• Operations are fragile and error-prone
• Consistency is critical
• A specific sequence must be followed

Example:

````markdown

Database migration

Run exactly this script:

python scripts/migrate.py --verify --backup

Do not modify the command or add additional flags. ````

Analogy: Think of Claude as a robot exploring a path:

• Narrow bridge with cliffs on both sides: There's only one safe way forward. Provide specific guardrails and exact instructions (low freedom). Example: database migrations that must run in exact sequence.
• Open field with no hazards: Many paths lead to success. Give general direction and trust Claude to find the best route (high freedom). Example: code reviews where context determines the best approach.

Test with all models you plan to use

Skills act as additions to models, so effectiveness depends on the underlying model. Test your Skill with all the models you plan to use it with.

Testing considerations by model:

• Claude Haiku (fast, economical): Does the Skill provide enough guidance?
• Claude Sonnet (balanced): Is the Skill clear and efficient?
• Claude Opus (powerful reasoning): Does the Skill avoid over-explaining?

What works perfectly for Opus might need more detail for Haiku. If you plan to use your Skill across multiple models, aim for instructions that work well with all of them.

Skill structure

<Note> YAML Frontmatter: The SKILL.md frontmatter requires two fields:

name:

• Maximum 64 characters
• Must contain only lowercase letters, numbers, and hyphens
• Cannot contain XML tags
• Cannot contain reserved words: "anthropic", "claude"

description:

• Must be non-empty
• Maximum 1024 characters
• Cannot contain XML tags
• Should describe what the Skill does and when to use it

For complete Skill structure details, see the Skills overview. </Note>

Naming conventions

Use consistent naming patterns to make Skills easier to reference and discuss. We recommend using gerund form (verb + -ing) for Skill names, as this clearly describes the activity or capability the Skill provides.

Remember that the name field must use lowercase letters, numbers, and hyphens only.

Good naming examples (gerund form):

• processing-pdfs
• analyzing-spreadsheets
• managing-databases
• testing-code
• writing-documentation

Acceptable alternatives:

• Noun phrases: pdf-processing, spreadsheet-analysis
• Action-oriented: process-pdfs, analyze-spreadsheets

Avoid:

• Vague names: helper, utils, tools
• Overly generic: documents, data, files
• Reserved words: anthropic-helper, claude-tools
• Inconsistent patterns within your skill collection

Consistent naming makes it easier to:

• Reference Skills in documentation and conversations
• Understand what a Skill does at a glance
• Organize and search through multiple Skills
• Maintain a professional, cohesive skill library

Writing effective descriptions

The description field enables Skill discovery and should include both what the Skill does and when to use it.

<Warning> Always write in third person. The description is injected into the system prompt, and inconsistent point-of-view can cause discovery problems.

• Good: "Processes Excel files and generates reports"
• Avoid: "I can help you process Excel files"
• Avoid: "You can use this to process Excel files"

</Warning>

Be specific and include key terms. Include both what the Skill does and specific triggers/contexts for when to use it.

Each Skill has exactly one description field. The description is critical for skill selection: Claude uses it to choose the right Skill from potentially 100+ available Skills. Your description must provide enough detail for Claude to know when to select this Skill, while the rest of SKILL.md provides the implementation details.

Effective examples:

PDF Processing skill:

description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

Excel Analysis skill:

description: Analyze Excel spreadsheets, create pivot tables, generate charts. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.

Git Commit Helper skill:

description: Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.

Avoid vague descriptions like these:

description: Helps with documents

description: Processes data

description: Does stuff with files

Progressive disclosure patterns

SKILL.md serves as an overview that points Claude to detailed materials as needed, like a table of contents in an onboarding guide. For an explanation of how progressive disclosure works, see How Skills work in the overview.

Practical guidance:

• Keep SKILL.md body under 500 lines for optimal performance
• Split content into separate files when approaching this limit
• Use the patterns below to organize instructions, code, and resources effectively

Visual overview: From simple to complex

A basic Skill starts with just a SKILL.md file containing metadata and instructions:

As your Skill grows, you can bundle additional content that Claude loads only when needed:

The complete Skill directory structure might look like this:

pdf/
├── SKILL.md              # Main instructions (loaded when triggered)
├── FORMS.md              # Form-filling guide (loaded as needed)
├── reference.md          # API reference (loaded as needed)
├── examples.md           # Usage examples (loaded as needed)
└── scripts/
    ├── analyze_form.py   # Utility script (executed, not loaded)
    ├── fill_form.py      # Form filling script
    └── validate.py       # Validation script

Pattern 1: High-level guide with references

````markdown --- name: pdf-processing description: Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction. ---

PDF Processing

Quick start

Extract text with pdfplumber:

import pdfplumber
with pdfplumber.open("file.pdf") as pdf:
    text = pdf.pages[0].extract_text()

Advanced features

Form filling: See FORMS.md for complete guide API reference: See REFERENCE.md for all methods Examples: See 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. When a user asks about sales metrics, Claude only needs to read sales-related schemas, not finance or marketing data. This keeps token usage low and context focused.

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

````markdown SKILL.md

BigQuery Data Analysis

Available datasets

Finance: Revenue, ARR, billing → See reference/finance.md Sales: Opportunities, pipeline, accounts → See reference/sales.md Product: API usage, features, adoption → See reference/product.md Marketing: Campaigns, attribution, email → See reference/marketing.md

Quick search

Find specific metrics using grep:

grep -i "revenue" reference/finance.md
grep -i "pipeline" reference/sales.md
grep -i "api usage" reference/product.md

````

Pattern 3: Conditional details

Show basic content, link to advanced content:

# DOCX Processing

## 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)

Claude reads REDLINING.md or OOXML.md only when the user needs those features.

Avoid deeply nested references

Claude may partially read files when they're referenced from other referenced files. When encountering nested references, Claude might use commands like head -100 to preview content rather than reading entire files, resulting in incomplete information.

Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md to ensure Claude reads complete files when needed.

Bad example: Too deep:

# SKILL.md

See [advanced.md](advanced.md)...

# advanced.md

See [details.md](details.md)...

# details.md

Here's the actual information...

Good example: One level deep:

# SKILL.md

**Basic usage**: [instructions in SKILL.md]
**Advanced features**: See [advanced.md](advanced.md)
**API reference**: See [reference.md](reference.md)
**Examples**: See [examples.md](examples.md)

Structure longer reference files with table of contents

For reference files longer than 100 lines, include a table of contents at the top. This ensures Claude can see the full scope of available information even when previewing with partial reads.

Example:

# API Reference

## Contents

- Authentication and setup
- Core methods (create, read, update, delete)
- Advanced features (batch operations, webhooks)
- Error handling patterns
- Code examples

## Authentication and setup

...

## Core methods

...

Claude can then read the complete file or jump to specific sections as needed.

For details on how this filesystem-based architecture enables progressive disclosure, see the Runtime environment section in the Advanced section below.

Workflows and feedback loops

Use workflows for complex tasks

Break complex operations into clear, sequential steps. For particularly complex workflows, provide a checklist that Claude can copy into its response and check off as it progresses.

Example 1: Research synthesis workflow (for Skills without code):

````markdown

Research synthesis workflow

Copy this checklist and track your progress:

Research Progress:
- [ ] Step 1: Read all source documents
- [ ] Step 2: Identify key themes
- [ ] Step 3: Cross-reference claims
- [ ] Step 4: Create structured summary
- [ ] Step 5: Verify citations

Step 1: Read all source documents

Review each document in the sources/ directory. Note the main arguments and supporting evidence.

Step 2: Identify key themes

Look for patterns across sources. What themes appear repeatedly? Where do sources agree or disagree?

Step 3: Cross-reference claims

For each major claim, verify it appears in the source material. Note which source supports each point.

Step 4: Create structured summary

Organize findings by theme. Include:

• Main claim
• Supporting evidence from sources
• Conflicting viewpoints (if any)

Step 5: Verify citations

Check that every claim references the correct source document. If citations are incomplete, return to Step 3. ````

This example shows how workflows apply to analysis tasks that don't require code. The checklist pattern works for any complex, multi-step process.

Example 2: PDF form filling workflow (for Skills with code):

````markdown

PDF form filling workflow

Copy this checklist and check off items as you complete them:

Task Progress:
- [ ] Step 1: Analyze the form (run analyze_form.py)
- [ ] Step 2: Create field mapping (edit fields.json)
- [ ] Step 3: Validate mapping (run validate_fields.py)
- [ ] Step 4: Fill the form (run fill_form.py)
- [ ] Step 5: Verify output (run verify_output.py)

Step 1: Analyze the form

Run: python scripts/analyze_form.py input.pdf

This extracts form fields and their locations, saving to fields.json.

Step 2: Create field mapping

Edit fields.json to add values for each field.

Step 3: Validate mapping

Run: python scripts/validate_fields.py fields.json

Fix any validation errors before continuing.

Step 4: Fill the form

Run: python scripts/fill_form.py input.pdf fields.json output.pdf

Step 5: Verify output

Run: python scripts/verify_output.py output.pdf

If verification fails, return to Step 2. ````

Clear steps prevent Claude from skipping critical validation. The checklist helps both Claude and you track progress through multi-step workflows.

Implement feedback loops

Common pattern: Run validator → fix errors → repeat

This pattern greatly improves output quality.

Example 1: Style guide compliance (for Skills without code):

## Content review process

1. Draft your content following the guidelines in STYLE_GUIDE.md
2. Review against the checklist:
   - Check terminology consistency
   - Verify examples follow the standard format
   - Confirm all required sections are present
3. If issues found:
   - Note each issue with specific section reference
   - Revise the content
   - Review the checklist again
4. Only proceed when all requirements are met
5. Finalize and save the document

This shows the validation loop pattern using reference documents instead of scripts. The "validator" is STYLE_GUIDE.md, and Claude performs the check by reading and comparing.

Example 2: Document editing process (for Skills with code):

## Document editing process

1. Make your edits to `word/document.xml`
2. **Validate immediately**: `python ooxml/scripts/validate.py unpacked_dir/`
3. If validation fails:
   - Review the error message carefully
   - Fix the issues in the XML
   - Run validation again
4. **Only proceed when validation passes**
5. Rebuild: `python ooxml/scripts/pack.py unpacked_dir/ output.docx`
6. Test the output document

The validation loop catches errors early.

Content guidelines

Avoid time-sensitive information

Don't include information that will become outdated:

Bad example: Time-sensitive (will become wrong):

If you're doing this before August 2025, use the old API.
After August 2025, use the new API.

Good example (use "old patterns" section):

## Current method

Use the v2 API endpoint: `api.example.com/v2/messages`

## Old patterns

<details>
<summary>Legacy v1 API (deprecated 2025-08)</summary>

The v1 API used: `api.example.com/v1/messages`

This endpoint is no longer supported.

</details>

The old patterns section provides historical context without cluttering the main content.

Use consistent terminology

Choose one term and use it throughout the Skill:

Good - Consistent:

• Always "API endpoint"
• Always "field"
• Always "extract"

Bad - Inconsistent:

• Mix "API endpoint", "URL", "API route", "path"
• Mix "field", "box", "element", "control"
• Mix "extract", "pull", "get", "retrieve"

Consistency helps Claude understand and follow instructions.

Common patterns

Template pattern

Provide templates for output format. Match the level of strictness to your needs.

For strict requirements (like API responses or data formats):

````markdown

Report structure

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary

[One-paragraph overview of key findings]

## Key findings

- Finding 1 with supporting data
- Finding 2 with supporting data
- Finding 3 with supporting data

## Recommendations

1. Specific actionable recommendation
2. Specific actionable recommendation

````

For flexible guidance (when adaptation is useful):

````markdown

Report structure

Here is a sensible default format, but use your best judgment based on the analysis:

# [Analysis Title]

## Executive summary

[Overview]

## Key findings

[Adapt sections based on what you discover]

## Recommendations

[Tailor to the specific context]

Adjust sections as needed for the specific analysis type. ````

Examples pattern

For Skills where output quality depends on seeing examples, provide input/output pairs just like in regular prompting:

````markdown

Commit message format

Generate commit messages following these examples:

Example 1: Input: Added user authentication with JWT tokens Output:

feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware

Example 2: Input: Fixed bug where dates displayed incorrectly in reports Output:

fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation

Example 3: Input: Updated dependencies and refactored error handling Output:

chore: update dependencies and refactor error handling

- Upgrade lodash to 4.17.21
- Standardize error response format across endpoints

Follow this style: type(scope): brief description, then detailed explanation. ````

Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.

Conditional workflow pattern

Guide Claude through decision points:

## Document modification workflow

1. Determine the modification type:

   **Creating new content?** → Follow "Creation workflow" below
   **Editing existing content?** → Follow "Editing workflow" below

2. Creation workflow:

   - Use docx-js library
   - Build document from scratch
   - Export to .docx format

3. Editing workflow:
   - Unpack existing document
   - Modify XML directly
   - Validate after each change
   - Repack when complete

<Tip> If workflows become large or complicated with many steps, consider pushing them into separate files and tell Claude to read the appropriate file based on the task at hand. </Tip>

Evaluation and iteration

Build evaluations first

Create evaluations BEFORE writing extensive documentation. This ensures your Skill solves real problems rather than documenting imagined ones.

Evaluation-driven development:

1. Identify gaps: Run Claude on representative tasks without a Skill. Document specific failures or missing context 2. Create evaluations: Build three scenarios that test these gaps 3. Establish baseline: Measure Claude's performance without the Skill 4. Write minimal instructions: Create just enough content to address the gaps and pass evaluations 5. Iterate: Execute evaluations, compare against baseline, and refine

This approach ensures you're solving actual problems rather than anticipating requirements that may never materialize.

Evaluation structure:

{
  "skills": ["pdf-processing"],
  "query": "Extract all text from this PDF file and save it to output.txt",
  "files": ["test-files/document.pdf"],
  "expected_behavior": [
    "Successfully reads the PDF file using an appropriate PDF processing library or command-line tool",
    "Extracts text content from all pages in the document without missing any pages",
    "Saves the extracted text to a file named output.txt in a clear, readable format"
  ]
}

<Note> This example demonstrates a data-driven evaluation with a simple testing rubric. We do not currently provide a built-in way to run these evaluations. Users can create their own evaluation system. Evaluations are your source of truth for measuring Skill effectiveness. </Note>

Develop Skills iteratively with Claude

The most effective Skill development process involves Claude itself. Work with one instance of Claude ("Claude A") to create a Skill that will be used by other instances ("Claude B"). Claude A helps you design and refine instructions, while Claude B tests them in real tasks. This works because Claude models understand both how to write effective agent instructions and what information agents need.

Creating a new Skill:

1. Complete a task without a Skill: Work through a problem with Claude A using normal prompting. As you work, you'll naturally provide context, explain preferences, and share procedural knowledge. Notice what information you repeatedly provide.

2. Identify the reusable pattern: After completing the task, identify what context you provided that would be useful for similar future tasks.

Example: If you worked through a BigQuery analysis, you might have provided table names, field definitions, filtering rules (like "always exclude test accounts"), and common query patterns.

3. Ask Claude A to create a Skill: "Create a Skill that captures this BigQuery analysis pattern we just used. Include the table schemas, naming conventions, and the rule about filtering test accounts."

<Tip> Claude models understand the Skill format and structure natively. You don't need special system prompts or a "writing skills" skill to get Claude to help create Skills. Simply ask Claude to create a Skill and it will generate properly structured SKILL.md content with appropriate frontmatter and body content. </Tip>

4. Review for conciseness: Check that Claude A hasn't added unnecessary explanations. Ask: "Remove the explanation about what win rate means - Claude already knows that."

5. Improve information architecture: Ask Claude A to organize the content more effectively. For example: "Organize this so the table schema is in a separate reference file. We might add more tables later."

6. Test on similar tasks: Use the Skill with Claude B (a fresh instance with the Skill loaded) on related use cases. Observe whether Claude B finds the right information, applies rules correctly, and handles the task successfully.

7. Iterate based on observation: If Claude B struggles or misses something, return to Claude A with specifics: "When Claude used this Skill, it forgot to filter by date for Q4. Should we add a section about date filtering patterns?"

Iterating on existing Skills:

The same hierarchical pattern continues when improving Skills. You alternate between:

• Working with Claude A (the expert who helps refine the Skill)
• Testing with Claude B (the agent using the Skill to perform real work)
• Observing Claude B's behavior and bringing insights back to Claude A

1. Use the Skill in real workflows: Give Claude B (with the Skill loaded) actual tasks, not test scenarios

2. Observe Claude B's behavior: Note where it struggles, succeeds, or makes unexpected choices

Example observation: "When I asked Claude B for a regional sales report, it wrote the query but forgot to filter out test accounts, even though the Skill mentions this rule."

3. Return to Claude A for improvements: Share the current SKILL.md and describe what you observed. Ask: "I noticed Claude B forgot to filter test accounts when I asked for a regional report. The Skill mentions filtering, but maybe it's not prominent enough?"

4. Review Claude A's suggestions: Claude A might suggest reorganizing to make rules more prominent, using stronger language like "MUST filter" instead of "always filter", or restructuring the workflow section.

5. Apply and test changes: Update the Skill with Claude A's refinements, then test again with Claude B on similar requests

6. Repeat based on usage: Continue this observe-refine-test cycle as you encounter new scenarios. Each iteration improves the Skill based on real agent behavior, not assumptions.

Gathering team feedback:

1. Share Skills with teammates and observe their usage 2. Ask: Does the Skill activate when expected? Are instructions clear? What's missing? 3. Incorporate feedback to address blind spots in your own usage patterns

Why this approach works: Claude A understands agent needs, you provide domain expertise, Claude B reveals gaps through real usage, and iterative refinement improves Skills based on observed behavior rather than assumptions.

Observe how Claude navigates Skills

As you iterate on Skills, pay attention to how Claude actually uses them in practice. Watch for:

• Unexpected exploration paths: Does Claude read files in an order you didn't anticipate? This might indicate your structure isn't as intuitive as you thought
• Missed connections: Does Claude fail to follow references to important files? Your links might need to be more explicit or prominent
• Overreliance on certain sections: If Claude repeatedly reads the same file, consider whether that content should be in the main SKILL.md instead
• Ignored content: If Claude never accesses a bundled file, it might be unnecessary or poorly signaled in the main instructions

Iterate based on these observations rather than assumptions. The 'name' and 'description' in your Skill's metadata are particularly critical. Claude uses these when deciding whether to trigger the Skill in response to the current task. Make sure they clearly describe what the Skill does and when it should be used.

Anti-patterns to avoid

Avoid Windows-style paths

Always use forward slashes in file paths, even on Windows:

• ✓ Good: scripts/helper.py, reference/guide.md
• ✗ Avoid: scripts\helper.py, reference\guide.md

Unix-style paths work across all platforms, while Windows-style paths cause errors on Unix systems.

Avoid offering too many options

Don't present multiple approaches unless necessary:

````markdown Bad example: Too many choices (confusing): "You can use pypdf, or pdfplumber, or PyMuPDF, or pdf2image, or..."

Good example: Provide a default (with escape hatch): "Use pdfplumber for text extraction:

import pdfplumber

For scanned PDFs requiring OCR, use pdf2image with pytesseract instead." ````

Advanced: Skills with executable code

The sections below focus on Skills that include executable scripts. If your Skill uses only markdown instructions, skip to Checklist for effective Skills.

Solve, don't punt

When writing scripts for Skills, handle error conditions rather than punting to Claude.

Good example: Handle errors explicitly:

def process_file(path):
    """Process a file, creating it if it doesn't exist."""
    try:
        with open(path) as f:
            return f.read()
    except FileNotFoundError:
        # Create file with default content instead of failing
        print(f"File {path} not found, creating default")
        with open(path, 'w') as f:
            f.write('')
        return ''
    except PermissionError:
        # Provide alternative instead of failing
        print(f"Cannot access {path}, using default")
        return ''

Bad example: Punt to Claude:

def process_file(path):
    # Just fail and let Claude figure it out
    return open(path).read()

Configuration parameters should also be justified and documented to avoid "voodoo constants" (Ousterhout's law). If you don't know the right value, how will Claude determine it?

Good example: Self-documenting:

# HTTP requests typically complete within 30 seconds
# Longer timeout accounts for slow connections
REQUEST_TIMEOUT = 30

# Three retries balances reliability vs speed
# Most intermittent failures resolve by the second retry
MAX_RETRIES = 3

Bad example: Magic numbers:

TIMEOUT = 47  # Why 47?
RETRIES = 5   # Why 5?

Provide utility scripts

Even if Claude could write a script, pre-made scripts offer advantages:

Benefits of utility scripts:

• More reliable than generated code
• Save tokens (no need to include code in context)
• Save time (no code generation required)
• Ensure consistency across uses

The diagram above shows how executable scripts work alongside instruction files. The instruction file (forms.md) references the script, and Claude can execute it without loading its contents into context.

Important distinction: Make clear in your instructions whether Claude should:

• Execute the script (most common): "Run analyze_form.py to extract fields"
• Read it as reference (for complex logic): "See analyze_form.py for the field extraction algorithm"

For most utility scripts, execution is preferred because it's more reliable and efficient. See the Runtime environment section below for details on how script execution works.

Example:

````markdown

Utility scripts

analyze_form.py: Extract all form fields from PDF

python scripts/analyze_form.py input.pdf > fields.json

Output format:

{
  "field_name": { "type": "text", "x": 100, "y": 200 },
  "signature": { "type": "sig", "x": 150, "y": 500 }
}

validate_boxes.py: Check for overlapping bounding boxes

python scripts/validate_boxes.py fields.json
# Returns: "OK" or lists conflicts

fill_form.py: Apply field values to PDF

python scripts/fill_form.py input.pdf fields.json output.pdf

````

Use visual analysis

When inputs can be rendered as images, have Claude analyze them:

````markdown

Form layout analysis

1. Convert PDF to images:

   python scripts/pdf_to_images.py form.pdf

2. Analyze each page image to identify form fields 3. Claude can see field locations and types visually ````

<Note> In this example, you'd need to write the pdf_to_images.py script. </Note>

Claude's vision capabilities help understand layouts and structures.

Create verifiable intermediate outputs

When Claude performs complex, open-ended tasks, it can make mistakes. The "plan-validate-execute" pattern catches errors early by having Claude first create a plan in a structured format, then validate that plan with a script before executing it.

Example: Imagine asking Claude to update 50 form fields in a PDF based on a spreadsheet. Without validation, Claude might reference non-existent fields, create conflicting values, miss required fields, or apply updates incorrectly.

Solution: Use the workflow pattern shown above (PDF form filling), but add an intermediate changes.json file that gets validated before applying changes. The workflow becomes: analyze → create plan file → validate plan → execute → verify.

Why this pattern works:

• Catches errors early: Validation finds problems before changes are applied
• Machine-verifiable: Scripts provide objective verification
• Reversible planning: Claude can iterate on the plan without touching originals
• Clear debugging: Error messages point to specific problems

When to use: Batch operations, destructive changes, complex validation rules, high-stakes operations.

Implementation tip: Make validation scripts verbose with specific error messages like "Field 'signature_date' not found. Available fields: customer_name, order_total, signature_date_signed" to help Claude fix issues.

Package dependencies

Skills run in the code execution environment with platform-specific limitations:

• claude.ai: Can install packages from npm and PyPI and pull from GitHub repositories
• Anthropic API: Has no network access and no runtime package installation

List required packages in your SKILL.md and verify they're available in the code execution tool documentation.

Runtime environment

Skills run in a code execution environment with filesystem access, bash commands, and code execution capabilities. For the conceptual explanation of this architecture, see The Skills architecture in the overview.

How this affects your authoring:

How Claude accesses Skills:

1. Metadata pre-loaded: At startup, the name and description from all Skills' YAML frontmatter are loaded into the system prompt 2. Files read on-demand: Claude uses bash Read tools to access SKILL.md and other files from the filesystem when needed 3. Scripts executed efficiently: Utility scripts can be executed via bash without loading their full contents into context. Only the script's output consumes tokens 4. No context penalty for large files: Reference files, data, or documentation don't consume context tokens until actually read

• File paths matter: Claude navigates your skill directory like a filesystem. Use forward slashes (reference/guide.md), not backslashes
• Name files descriptively: Use names that indicate content: form_validation_rules.md, not doc2.md
• Organize for discovery: Structure directories by domain or feature
• Good: reference/finance.md, reference/sales.md
• Bad: docs/file1.md, docs/file2.md
• Bundle comprehensive resources: Include complete API docs, extensive examples, large datasets; no context penalty until accessed
• Prefer scripts for deterministic operations: Write validate_form.py rather than asking Claude to generate validation code
• Make execution intent clear:
• "Run analyze_form.py to extract fields" (execute)
• "See analyze_form.py for the extraction algorithm" (read as reference)
• Test file access patterns: Verify Claude can navigate your directory structure by testing with real requests

Example:

bigquery-skill/
├── SKILL.md (overview, points to reference files)
└── reference/
    ├── finance.md (revenue metrics)
    ├── sales.md (pipeline data)
    └── product.md (usage analytics)

When the user asks about revenue, Claude reads SKILL.md, sees the reference to reference/finance.md, and invokes bash to read just that file. The sales.md and product.md files remain on the filesystem, consuming zero context tokens until needed. This filesystem-based model is what enables progressive disclosure. Claude can navigate and selectively load exactly what each task requires.

For complete details on the technical architecture, see How Skills work in the Skills overview.

MCP tool references

If your Skill uses MCP (Model Context Protocol) tools, always use fully qualified tool names to avoid "tool not found" errors.

Format: ServerName:tool_name

Example:

Use the BigQuery:bigquery_schema tool to retrieve table schemas.
Use the GitHub:create_issue tool to create issues.

Where:

• BigQuery and GitHub are MCP server names
• bigquery_schema and create_issue are the tool names within those servers

Without the server prefix, Claude may fail to locate the tool, especially when multiple MCP servers are available.

Avoid assuming tools are installed

Don't assume packages are available:

````markdown Bad example: Assumes installation: "Use the pdf library to process the file."

Good example: Explicit about dependencies: "Install required package: pip install pypdf

Then use it:

```python from pypdf import PdfReader reader = PdfReader("file.pdf") `" `` ```

Technical notes

YAML frontmatter requirements

The SKILL.md frontmatter requires name and description fields with specific validation rules:

• name: Maximum 64 characters, lowercase letters/numbers/hyphens only, no XML tags, no reserved words
• description: Maximum 1024 characters, non-empty, no XML tags

See the Skills overview for complete structure details.

Token budgets

Keep SKILL.md body under 500 lines for optimal performance. If your content exceeds this, split it into separate files using the progressive disclosure patterns described earlier. For architectural details, see the Skills overview.

Checklist for effective Skills

Before sharing a Skill, verify:

Core quality

• [ ] Description is specific and includes key terms
• [ ] Description includes both what the Skill does and when to use it
• [ ] SKILL.md body is under 500 lines
• [ ] Additional details are in separate files (if needed)
• [ ] No time-sensitive information (or in "old patterns" section)
• [ ] Consistent terminology throughout
• [ ] Examples are concrete, not abstract
• [ ] File references are one level deep
• [ ] Progressive disclosure used appropriately
• [ ] Workflows have clear steps

Code and scripts

• [ ] Scripts solve problems rather than punt to Claude
• [ ] Error handling is explicit and helpful
• [ ] No "voodoo constants" (all values justified)
• [ ] Required packages listed in instructions and verified as available
• [ ] Scripts have clear documentation
• [ ] No Windows-style paths (all forward slashes)
• [ ] Validation/verification steps for critical operations
• [ ] Feedback loops included for quality-critical tasks

Testing

• [ ] At least three evaluations created
• [ ] Tested with Haiku, Sonnet, and Opus
• [ ] Tested with real usage scenarios
• [ ] Team feedback incorporated (if applicable)

Next steps

<CardGroup cols={2}> <Card title="Get started with Agent Skills" icon="rocket" href="/docs/en/agents-and-tools/agent-skills/quickstart" > Create your first Skill </Card> <Card title="Use Skills in Claude Code" icon="terminal" href="https://code.claude.com/docs/en/skills" > Create and manage Skills in Claude Code </Card> <Card title="Use Skills in the Agent SDK" icon="cube" href="/docs/en/agent-sdk/skills" > Use Skills programmatically in TypeScript and Python </Card> <Card title="Use Skills with the API" icon="code" href="/docs/en/build-with-claude/skills-guide" > Upload and use Skills programmatically </Card> </CardGroup>

Agent Skills

Create, manage, and share Skills to extend Claude's capabilities in Claude Code.

This guide shows you how to create, use, and manage Agent Skills in Claude Code. Skills are modular capabilities that extend Claude's functionality through organized folders containing instructions, scripts, and resources.

Prerequisites

• Claude Code version 1.0 or later
• Basic familiarity with Claude Code

What are Agent Skills?

Agent Skills package expertise into discoverable capabilities. Each Skill consists of a SKILL.md file with instructions that Claude reads when relevant, plus optional supporting files like scripts and templates.

How Skills are invoked: Skills are model-invoked—Claude autonomously decides when to use them based on your request and the Skill's description. This is different from slash commands, which are user-invoked (you explicitly type /command to trigger them).

Benefits:

• Extend Claude's capabilities for your specific workflows
• Share expertise across your team via git
• Reduce repetitive prompting
• Compose multiple Skills for complex tasks

Learn more in the Agent Skills overview.

<Note> For a deep dive into the architecture and real-world applications of Agent Skills, read our engineering blog: Equipping agents for the real world with Agent Skills. </Note>

Create a Skill

Skills are stored as directories containing a SKILL.md file.

Personal Skills

Personal Skills are available across all your projects. Store them in ~/.claude/skills/:

```bash theme={null} mkdir -p ~/.claude/skills/my-skill-name

**Use personal Skills for**:

- Your individual workflows and preferences
- Experimental Skills you're developing
- Personal productivity tools

### Project Skills

Project Skills are shared with your team. Store them in `.claude/skills/` within your project:

mkdir -p .claude/skills/my-skill-name

**Use project Skills for**:

- Team workflows and conventions
- Project-specific expertise
- Shared utilities and scripts

Project Skills are checked into git and automatically available to team members.

### Plugin Skills

Skills can also come from [Claude Code plugins](/en/plugins). Plugins may bundle Skills that are automatically available when the plugin is installed. These Skills work the same way as personal and project Skills.

## Write SKILL.md

Create a `SKILL.md` file with YAML frontmatter and Markdown content:

--- name: your-skill-name description: Brief description of what this Skill does and when to use it ---

Your Skill Name

Instructions

Provide clear, step-by-step guidance for Claude.

Examples

Show concrete examples of using this Skill.

**Field requirements**:

- `name`: Must use lowercase letters, numbers, and hyphens only (max 64 characters)
- `description`: Brief description of what the Skill does and when to use it (max 1024 characters)

The `description` field is critical for Claude to discover when to use your Skill. It should include both what the Skill does and when Claude should use it.

See the [best practices guide](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices) for complete authoring guidance including validation rules.

## Add supporting files

Create additional files alongside SKILL.md:

my-skill/ ├── SKILL.md (required) ├── reference.md (optional documentation) ├── examples.md (optional examples) ├── scripts/ │ └── helper.py (optional utility) └── templates/ └── template.txt (optional template)

Reference these files from SKILL.md:

For advanced usage, see reference.md.

Run the helper script:

python scripts/helper.py input.txt

````

Claude reads these files only when needed, using progressive disclosure to manage context efficiently.

Restrict tool access with allowed-tools

Use the allowed-tools frontmatter field to limit which tools Claude can use when a Skill is active:

```yaml theme={null} --- name: safe-file-reader description: Read files without making changes. Use when you need read-only file access. allowed-tools: Read, Grep, Glob ---

Safe File Reader

This Skill provides read-only file access.

Instructions

1. Use Read to view file contents 2. Use Grep to search within files 3. Use Glob to find files by pattern

When this Skill is active, Claude can only use the specified tools (Read, Grep, Glob) without needing to ask for permission. This is useful for:

- Read-only Skills that shouldn't modify files
- Skills with limited scope: for example, only data analysis, no file writing
- Security-sensitive workflows where you want to restrict capabilities

If `allowed-tools` isn't specified, Claude will ask for permission to use tools as normal, following the standard permission model.

<Note>
  `allowed-tools` is only supported for Skills in Claude Code.
</Note>

## View available Skills

Skills are automatically discovered by Claude from three sources:

- Personal Skills: `~/.claude/skills/`
- Project Skills: `.claude/skills/`
- Plugin Skills: bundled with installed plugins

**To view all available Skills**, ask Claude directly:

What Skills are available?

or

List all available Skills

This will show all Skills from all sources, including plugin Skills.

**To inspect a specific Skill**, you can also check the filesystem:

List personal Skills

ls ~/.claude/skills/

List project Skills (if in a project directory)

ls .claude/skills/

View a specific Skill's content

cat ~/.claude/skills/my-skill/SKILL.md

## Test a Skill

After creating a Skill, test it by asking questions that match your description.

**Example**: If your description mentions "PDF files":

Can you help me extract text from this PDF?

Claude autonomously decides to use your Skill if it matches the request—you don't need to explicitly invoke it. The Skill activates automatically based on the context of your question.

## Debug a Skill

If Claude doesn't use your Skill, check these common issues:

### Make description specific

**Too vague**:

description: Helps with documents

**Specific**:

description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

Include both what the Skill does and when to use it in the description.

### Verify file path

**Personal Skills**: `~/.claude/skills/skill-name/SKILL.md`
**Project Skills**: `.claude/skills/skill-name/SKILL.md`

Check the file exists:

Personal

ls ~/.claude/skills/my-skill/SKILL.md

Project

ls .claude/skills/my-skill/SKILL.md

### Check YAML syntax

Invalid YAML prevents the Skill from loading. Verify the frontmatter:

cat SKILL.md | head -n 10

Ensure:

- Opening `---` on line 1
- Closing `---` before Markdown content
- Valid YAML syntax (no tabs, correct indentation)

### View errors

Run Claude Code with debug mode to see Skill loading errors:

claude --debug

## Share Skills with your team

**Recommended approach**: Distribute Skills through [plugins](/en/plugins).

To share Skills via plugin:

1. Create a plugin with Skills in the `skills/` directory
2. Add the plugin to a marketplace
3. Team members install the plugin

For complete instructions, see [Add Skills to your plugin](/en/plugins#add-skills-to-your-plugin).

You can also share Skills directly through project repositories:

### Step 1: Add Skill to your project

Create a project Skill:

mkdir -p .claude/skills/team-skill

Create SKILL.md

### Step 2: Commit to git

git add .claude/skills/ git commit -m "Add team Skill for PDF processing" git push

### Step 3: Team members get Skills automatically

When team members pull the latest changes, Skills are immediately available:

git pull claude # Skills are now available

## Update a Skill

Edit SKILL.md directly:

Personal Skill

code ~/.claude/skills/my-skill/SKILL.md

Project Skill

code .claude/skills/my-skill/SKILL.md

Changes take effect the next time you start Claude Code. If Claude Code is already running, restart it to load the updates.

## Remove a Skill

Delete the Skill directory:

Personal

rm -rf ~/.claude/skills/my-skill

Project

rm -rf .claude/skills/my-skill git commit -m "Remove unused Skill"

## Best practices

### Keep Skills focused

One Skill should address one capability:

**Focused**:

- "PDF form filling"
- "Excel data analysis"
- "Git commit messages"

**Too broad**:

- "Document processing" (split into separate Skills)
- "Data tools" (split by data type or operation)

### Write clear descriptions

Help Claude discover when to use Skills by including specific triggers in your description:

**Clear**:

description: Analyze Excel spreadsheets, create pivot tables, and generate charts. Use when working with Excel files, spreadsheets, or analyzing tabular data in .xlsx format.

**Vague**:

description: For files

### Test with your team

Have teammates use Skills and provide feedback:

- Does the Skill activate when expected?
- Are the instructions clear?
- Are there missing examples or edge cases?

### Document Skill versions

You can document Skill versions in your SKILL.md content to track changes over time. Add a version history section:

My Skill

Version History

• v2.0.0 (2025-10-01): Breaking changes to API
• v1.1.0 (2025-09-15): Added new features
• v1.0.0 (2025-09-01): Initial release

This helps team members understand what changed between versions.

## Troubleshooting

### Claude doesn't use my Skill

**Symptom**: You ask a relevant question but Claude doesn't use your Skill.

**Check**: Is the description specific enough?

Vague descriptions make discovery difficult. Include both what the Skill does and when to use it, with key terms users would mention.

**Too generic**:

description: Helps with data

**Specific**:

description: Analyze Excel spreadsheets, generate pivot tables, create charts. Use when working with Excel files, spreadsheets, or .xlsx files.

**Check**: Is the YAML valid?

Run validation to check for syntax errors:

View frontmatter

cat .claude/skills/my-skill/SKILL.md | head -n 15

Check for common issues

- Missing opening or closing ---

- Tabs instead of spaces

- Unquoted strings with special characters

**Check**: Is the Skill in the correct location?

Personal Skills

ls ~/.claude/skills/*/SKILL.md

Project Skills

ls .claude/skills/*/SKILL.md

### Skill has errors

**Symptom**: The Skill loads but doesn't work correctly.

**Check**: Are dependencies available?

Claude will automatically install required dependencies (or ask for permission to install them) when it needs them.

**Check**: Do scripts have execute permissions?

chmod +x .claude/skills/my-skill/scripts/*.py

**Check**: Are file paths correct?

Use forward slashes (Unix style) in all paths:

**Correct**: `scripts/helper.py`
**Wrong**: `scripts\helper.py` (Windows style)

### Multiple Skills conflict

**Symptom**: Claude uses the wrong Skill or seems confused between similar Skills.

**Be specific in descriptions**: Help Claude choose the right Skill by using distinct trigger terms in your descriptions.

Instead of:

Skill 1

description: For data analysis

Skill 2

description: For analyzing data

Use:

Skill 1

description: Analyze sales data in Excel files and CRM exports. Use for sales reports, pipeline analysis, and revenue tracking.

Skill 2

description: Analyze log files and system metrics data. Use for performance monitoring, debugging, and system diagnostics.

## Examples

### Simple Skill (single file)

commit-helper/ └── SKILL.md

--- name: generating-commit-messages description: Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes. ---

Generating Commit Messages

Instructions

1. Run git diff --staged to see changes 2. I'll suggest a commit message with:

• Summary under 50 characters
• Detailed description
• Affected components

Best practices

• Use present tense
• Explain what and why, not how

### Skill with tool permissions

code-reviewer/ └── SKILL.md

--- name: code-reviewer description: Review code for best practices and potential issues. Use when reviewing code, checking PRs, or analyzing code quality. allowed-tools: Read, Grep, Glob ---

Code Reviewer

Review checklist

1. Code organization and structure 2. Error handling 3. Performance considerations 4. Security concerns 5. Test coverage

Instructions

1. Read the target files using Read tool 2. Search for patterns using Grep 3. Find related files using Glob 4. Provide detailed feedback on code quality

### Multi-file Skill

pdf-processing/ ├── SKILL.md ├── FORMS.md ├── REFERENCE.md └── scripts/ ├── fill_form.py └── validate.py

**SKILL.md**:

--- name: pdf-processing description: Extract text, fill forms, merge PDFs. Use when working with PDF files, forms, or document extraction. Requires pypdf and pdfplumber packages. ---

PDF Processing

Quick start

Extract text:

import pdfplumber
with pdfplumber.open("doc.pdf") as pdf:
    text = pdf.pages[0].extract_text()

For form filling, see FORMS.md. For detailed API reference, see REFERENCE.md.

Requirements

Packages must be installed in your environment:

pip install pypdf pdfplumber

````

<Note> List required packages in the description. Packages must be installed in your environment before Claude can use them. </Note>

Claude loads additional files only when needed.

SKILL.md Template

YAML Frontmatter

---
name: [skill-name]
description: [Action verb] [what it does]. Use when [trigger conditions] or when user mentions [keywords].
---

Frontmatter Rules:

• name: Max 64 chars, lowercase letters/numbers/hyphens only, no reserved words (anthropic, claude)
• description: Max 1024 chars, third person voice, includes what AND when to use

Body Structure

**Goal**: [One sentence describing the skill's purpose]

**IMPORTANT**: [Critical constraint or principle - optional]

## Workflow

### Phase 1: [Phase Name]

- [Task 1]
- [Task 2]
- [Task 3]

### Phase 2: [Phase Name]

- [Task 1]
- [Task 2]
- [Task 3]

### Phase 3: [Phase Name]

- [Task 1]
- [Task 2]
- [Task 3]

## Rules

- [Constraint 1]
- [Constraint 2]
- [Constraint 3]

## Acceptance Criteria

- [Criterion 1]
- [Criterion 2]
- [Criterion 3]

Guidelines

Naming Convention

Use gerund form (verb + -ing):

• processing-pdfs
• analyzing-spreadsheets
• managing-databases

Description Pattern

[Verb]s [objects/actions]. Use when [specific triggers] or when user mentions [keywords].

Examples:

• "Extracts text from PDF files and fills forms. Use when working with PDFs or when user mentions document extraction."
• "Generates commit messages by analyzing git diffs. Use when user asks for help with commit messages."

Content Principles

1. Be concise - Only add context Claude doesn't already know 2. One level deep - Reference files directly from SKILL.md, avoid nested references 3. Under 500 lines - Split into separate files if content exceeds this 4. Consistent terminology - Use same terms throughout (don't mix "field"/"box"/"element") 5. No time-sensitive info - Avoid dates or version-specific content that will become outdated