Skill Creator
Tools for creating and validating Agent Skills.
About Skills
Skills are modular, self-contained packages that extend an Agent's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform an Agent from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
What Skills Provide
- Specialized workflows - Multi-step procedures for specific domains
- Tool integrations - Instructions for working with specific file formats or APIs
- Domain expertise - Company-specific knowledge, schemas, business logic
- 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 the Agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: The Agent is already very smart. Only add context the Agent doesn't already have. Challenge each piece of information: "Does the Agent 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 an Agent as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Skill Structure
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 and fields. These are the only fields that the Agent 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).
Resource Directories
| Directory | When to include | Examples |
|---|
| Skills requiring Python scripts | , |
| Detailed documentation for agent reference | , |
| Templates, boilerplate, or files for output | , |
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: for PDF rotation tasks
- Benefits: Token efficient, deterministic, may be executed without loading into context
- Note: Scripts may still need to be read by Agent for patching or environment-specific adjustments
References ()
Documentation and reference material intended to be loaded as needed into context to inform Agent's process and thinking.
- When to include: For documentation that Agent should reference while working
- Examples: for financial schemas, for company NDA template, for company policies, for API specifications
- Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
- Benefits: Keeps SKILL.md lean, loaded only when Agent 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 ()
Files not intended to be loaded into context, but rather used within the output Agent produces.
- When to include: When the skill needs files that will be used in the final output
- Examples: for brand assets, for PowerPoint templates,
assets/frontend-template/
- Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
- Benefits: Separates output resources from documentation, enables Agent 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, including:
- README.md
- INSTALLATION_GUIDE.md
- QUICK_REFERENCE.md
- CHANGELOG.md
- etc.
The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxiliary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
Progressive Disclosure Design Principle
Skills use a three-level loading system to manage context efficiently:
- Metadata (name + description) - Always in context (~100 words)
- SKILL.md body - When skill triggers (<5k words)
- Bundled resources - As needed by Agent (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, to ensure the reader of the skill knows they exist and when to use 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 (patterns, examples, configuration) into separate reference files.
Pattern 1: High-level guide with references
markdown
# 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
The Agent 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)
├── product.md (API usage, features)
└── marketing.md (campaigns, attribution)
When a user asks about sales metrics, the Agent only reads sales.md.
Similarly, for skills supporting multiple frameworks or variants, organize by variant:
cloud-deploy/
├── SKILL.md (workflow + provider selection)
└── references/
├── aws.md (AWS deployment patterns)
├── gcp.md (GCP deployment patterns)
└── azure.md (Azure deployment patterns)
When the user chooses AWS, the Agent only reads aws.md.
Pattern 3: Conditional details
markdown
# 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)
The Agent reads REDLINING.md or OOXML.md only when the user needs those features.
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 the Agent can see the full scope when previewing.
Skill Creation Process
Skill creation involves these steps:
- Understand the skill with concrete examples
- Plan reusable skill contents (scripts, references, assets)
- Initialize the skill
- Edit the skill (implement resources and write SKILL.md)
- Package the skill
- 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?"
- "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:
- Considering how to execute on the example from scratch
- Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly
Example: When building a
skill to handle queries like "Help me rotate this PDF," the analysis shows:
- Rotating a PDF requires re-writing the same code each time
- A script would be helpful to store in the skill
Example: When designing a
skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
- Writing a frontend webapp requires the same boilerplate HTML/React each time
- An template containing the boilerplate HTML/React project files would be helpful to store in the skill
Example: When building a
skill to handle queries like "How many users have logged in today?" the analysis shows:
- Querying BigQuery requires re-discovering the table schemas and relationships each time
- A 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: Initialize the Skill
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists. In this case, continue to the next step.
When creating a new skill from scratch, always run the
script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
Usage:
bash
uv run scripts/init.py <skill-name>
Optional flags to create resource directories:
bash
uv run scripts/init.py <skill-name> --script --ref --asset
The initialization script creates:
- Skill directory structure
- SKILL.md template with YAML frontmatter
Use flags to create resource directories as needed:
Step 2: Edit the Skill
When editing the (newly-generated or existing) skill, remember that the skill is being created for another Agent instance to use. Include information that would be beneficial and non-obvious to another Agent. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Agent execute these tasks more effectively.
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:
,
, and
files. Note that this step may require user input. For example, when implementing a
skill, the user may need to provide brand assets or templates to store in
, or documentation to store in
.
Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in
,
, and
to demonstrate structure, but most skills won't need all of them.
Add Scripts
Create Python scripts in
directory for tasks requiring deterministic reliability. Scripts should be idempotent and handle errors gracefully.
bash
# Add dependencies if needed
uv add <package-name>
# Run and test the script
uv run --frozen scripts/<script-name>.py <args>
Add References
Add documentation files in
for domain knowledge, schemas, API specs, or policies.
Add Assets
Add templates, boilerplate, or output files in
.
Update SKILL.md
Write the YAML frontmatter and Markdown body for the skill. See SKILL.md Writing Guidelines below.
Validate the Skill
You can run validation at any time:
bash
uv run scripts/validate.py <skill-directory>
To allow TODO placeholders in SKILL.md body (for skills like code-style that need TODO syntax):
bash
uv run scripts/validate.py <skill-directory> --allow-todos
Step 4: Iterate
After testing the skill, iterate based on real usage:
- Use the skill on actual tasks
- Notice struggles or inefficiencies
- Identify how SKILL.md or bundled resources should be updated
- Implement changes and test again
SKILL.md Writing Guidelines
YAML Frontmatter
Write the YAML frontmatter with
and
:
- : The skill name
- : This is the primary triggering mechanism for your skill, and helps the Agent 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, so "When to Use This Skill" sections in the body are not helpful to the Agent.
- Example: "Tool for creating and managing Agent Skills. Use when users want to create a new skill or manage existing skills. Supports initialization, validation, and iterative development workflows."
- Example description for a skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when the Agent needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
Do not include any other fields in YAML frontmatter.
Markdown Body
Write instructions for using the skill and its bundled resources. Use imperative/infinitive form.
Git Ignore
When creating a skill with Python scripts:
bash
cp .gitignore <skill-name>/.gitignore
This excludes
,
, and
from version control.
uv Commands
bash
uv init --bare # Initialize project
uv add <package-name> # Add dependency
uv remove <package-name> # Remove dependency
uv run --frozen scripts/<name>.py <args> # Run script
uv run scripts/<script-name>.py <args> # Run skill scripts
All skill-creator scripts use uv. If uv is not installed, ask the user to install it first.