Skip to main content

​
Directory structure

An Agent Skill is a directory containing at minimum a SKILL.md file. This format is widely used for creating Claude Skills: 
skill-name/
└── SKILL.md          # Required
You can optionally include additional directories such as scripts/, references/, and assets/ to support your Agent Skill.

​
SKILL.md format

The SKILL.md file is the core component of every Agent Skill. It must contain YAML frontmatter followed by Markdown content.

​
Frontmatter (required)

---
name: skill-name
description: A description of what this skill does and when to use it.
---
With optional fields: 
---
name: pdf-processing
description: Extract text and tables from PDF files, fill forms, merge documents.
license: Apache-2.0
metadata:
  author: example-org
  version: "1.0"
---
FieldRequiredConstraints
nameYesMax 64 characters. Lowercase letters, numbers, and hyphens only. Must not start or end with a hyphen.
descriptionYesMax 1024 characters. Non-empty. Describes what the Agent Skill does and when to use it.
licenseNoLicense name or reference to a bundled license file.
compatibilityNoMax 500 characters. Indicates environment requirements (intended product, system packages, network access, etc.).
metadataNoArbitrary key-value mapping for additional metadata.
allowed-toolsNoSpace-delimited list of pre-approved tools the Agent Skill may use. (Experimental)

​
name field

The required name field:
  • Must be 1-64 characters
  • May only contain unicode lowercase alphanumeric characters and hyphens (a-z and -)
  • Must not start or end with -
  • Must not contain consecutive hyphens (--)
  • Must match the parent directory name
Valid examples: 
name: pdf-processing

name: data-analysis

name: code-review
Invalid examples: 
name: PDF-Processing  # uppercase not allowed

name: -pdf  # cannot start with hyphen

name: pdf--processing  # consecutive hyphens not allowed

​
description field

The required description field:
  • Must be 1-1024 characters
  • Should describe both what the Agent Skill does and when to use it
  • Should include specific keywords that help agents identify relevant tasks
Good example: 
description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction.
Poor example: 
description: Helps with PDFs.

​
license field

The optional license field:
  • Specifies the license applied to the Agent Skill
  • We recommend keeping it short (either the name of a license or the name of a bundled license file)
Example: 
license: Proprietary. LICENSE.txt has complete terms

​
compatibility field

The optional compatibility field:
  • Must be 1-500 characters if provided
  • Should only be included if your Agent Skill has specific environment requirements
  • Can indicate intended product, required system packages, network access needs, etc.
Examples: 
compatibility: Designed for Claude Code (or similar products)

compatibility: Requires git, docker, jq, and access to the internet
Most Agent Skills do not need the compatibility field.

​
metadata field

The optional metadata field:
  • A map from string keys to string values
  • Clients can use this to store additional properties not defined by the Agent Skills specification. Claude Skills often use this field for custom versioning or author information.
  • We recommend making your key names reasonably unique to avoid accidental conflicts
Example: 
metadata:
  author: example-org
  version: "1.0"

​
allowed-tools field

The optional allowed-tools field:
  • A space-delimited list of tools that are pre-approved to run
  • Experimental. Support for this field may vary between agent implementations
Example: 
allowed-tools: Bash(git:*) Bash(jq:*) Read

​
Body content

The Markdown body after the frontmatter contains the Agent Skill instructions. There are no format restrictions. Write whatever helps agents perform the task effectively when using this Agent Skill. This instruction set is what guides a Claude Skill through complex workflows. Recommended sections:
  • Step-by-step instructions
  • Examples of inputs and outputs
  • Common edge cases
Note that the agent will load this entire file once it’s decided to activate an Agent Skill. Consider splitting longer SKILL.md content into referenced files.

​
Optional directories

Agent Skills can include optional directories to support more complex workflows.

​
scripts/

Contains executable code that agents can run when using the Agent Skill. Scripts should:
  • Be self-contained or clearly document dependencies
  • Include helpful error messages
  • Handle edge cases gracefully
Supported languages depend on the agent implementation. Common options include Python, Bash, and JavaScript.

​
references/

Contains additional documentation that agents can read when needed:
  • REFERENCE.md - Detailed technical reference
  • FORMS.md - Form templates or structured data formats
  • Domain-specific files (finance.md, legal.md, etc.)
Keep individual reference files focused. When agents use Agent Skills, they load these reference files on demand—a key principle for efficient Claude Skill execution.

​
assets/

Contains static resources:
  • Templates (document templates, configuration templates)
  • Images (diagrams, examples)
  • Data files (lookup tables, schemas)

​
Progressive disclosure

Agent Skills should be structured for efficient use of context. This structure is essential for high-performance Claude Skills:
  1. Metadata (~100 tokens): The name and description fields are loaded at startup for all Agent Skills
  2. Instructions (< 5000 tokens recommended): The full SKILL.md body is loaded when the Agent Skill or Claude Skill is activated
  3. Resources (as needed): Files (e.g. those in scripts/, references/, or assets/) are loaded only when required
Keep your main SKILL.md under 500 lines. Move detailed reference material to separate files.

​
File references

When referencing other files in your Agent Skill, use relative paths from the skill root: 
See [the reference guide](references/REFERENCE.md) for details.

Run the extraction script:
scripts/extract.py
Keep file references one level deep from SKILL.md. Avoid deeply nested reference chains.

​
Validation

Use the skills-ref reference library to validate your Agent Skills and ensure your Claude Skills are correctly formatted: 
skills-ref validate ./my-skill
This checks that your SKILL.md frontmatter is valid and follows all naming conventions.