| name | skill-writer |
| description | Create, revise, and validate effective skills. Use when adding a new skill or changing an existing skill's SKILL.md, bundled scripts, references, assets, scaffold templates, or validation tooling. |
| author | alexgorbatchev |
Skill Writer
This skill provides guidance for creating and revising 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
- 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 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.
Treat the frontmatter description as routing metadata, not as a mini playbook. It should help the agent decide whether to load the skill, not try to enforce workflow rules before the skill body is read.
Eliminate Prompt Debt and Redundancy
To keep skills highly efficient and avoid wasting tokens on useless meta-commentary:
- No Markdown Title/Headers: Do not start
SKILL.md with # Skill Name or similar. The model already knows the skill name from the metadata.
- No Overviews or Meta-Commentary: Do not add
## Overview or explanatory sentences like "This skill acts as a proxy..." or "Below are the guidelines...". Jump straight into the action, rules, or decision logic.
- Minimalist Descriptions: Strip the frontmatter
description to the absolute bare minimum needed to trigger. For example, use Use when asked to commit changes in a Git repository. instead of verbose sentences detailing every scenario.
- Remove Implied Steps: Do not write out steps that are completely obvious or implied. For example, if working with a review agent, do not instruct to "address issues" as that is the definition of pairing with a review agent.
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).
Portability (No Local References)
Skills must be portable and reusable across different environments, machines, and projects.
Never include local references or hardcoded absolute paths in your skill files (SKILL.md, scripts, references, etc.).
- Avoid paths like
/Users/alex/development/... or C:\Users\....
- Use relative paths, or environment variables, or parameterize paths so they are evaluated at runtime by the agent.
- When referring to other files within the skill itself, always use paths relative to the skill directory (e.g.,
scripts/my_script.ts or references/docs.md).
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)
│ │ └── author: alexgorbatchev (repo convention)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Bun/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):
name and description are the important triggering fields. In this repo, also include author: alexgorbatchev in skill frontmatter. Keep frontmatter minimal. In this toolchain, the validator requires name and description, permits author, and currently permits only license, allowed-tools, and metadata as additional keys beyond those. Default to name, description, and author unless you have a validated reason to add one of those supported extras.
- 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 (Bun/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.
Rule of thumb: If you're writing detailed configuration, setup steps, or reference material that exceeds ~50 lines, put it in references/filename.md and link to it from SKILL.md. Keep SKILL.md focused on workflows and decision guidance.
- When to include: For documentation that Claude should reference while working
- Examples:
references/finance.md for financial schemas, references/mnda.md for company NDA template, references/policies.md for company policies, references/api_docs.md for API specifications
- Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
- Service setup: Installation, configuration, and infrastructure setup details must be written to
references/setup.md - this keeps SKILL.md focused on workflows while preserving setup documentation for reference
- Benefits: Keeps SKILL.md lean, loaded only when Claude determines it's needed
- Best practice: If files are large (>10k words), include grep search patterns in SKILL.md
- Avoid duplication: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.
Assets (assets/)
Files not intended to be loaded into context, but rather used within the output Claude produces.
- When to include: When the skill needs files that will be used in the final output
- Examples:
assets/logo.png for brand assets, assets/slides.pptx for PowerPoint templates, assets/frontend-template/ for HTML/React boilerplate, assets/font.ttf for typography
- Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
- Benefits: Separates output resources from documentation, enables Claude to use files without loading them into context
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 auxilary 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 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, 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
# 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)
├── product.md (API usage, features)
└── marketing.md (campaigns, attribution)
When a user asks about sales metrics, Claude 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, Claude only reads aws.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.
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.
Skill Writing Process
Skill writing and maintenance involve these steps:
- Understand the skill with concrete examples
- Plan reusable skill contents (scripts, references, assets)
- Initialize the skill when needed (run
bun {{skills_dir}}/skill-writer/scripts/init_skill.ts)
- Edit the skill (implement resources and write SKILL.md)
- Validate the skill (run
bun {{skills_dir}}/skill-writer/scripts/quick_validate.ts)
- 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 pdf-editor 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
scripts/rotate_pdf.py script would be helpful to store in the skill
Example: When designing a frontend-webapp-builder skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
- Writing a frontend webapp requires the same boilerplate HTML/React each time
- An
assets/hello-world/ template containing the boilerplate HTML/React project files would be helpful to store in the skill
Example: When building a big-query skill to handle queries like "How many users have logged in today?" the analysis shows:
- Querying BigQuery requires re-discovering the table schemas and relationships each time
- A
references/schema.md file documenting the table schemas would be helpful to store in the skill
To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
Step 3: Initializing the Skill
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration or validation is needed. In this case, continue to the next step.
When creating a new skill from scratch, ALWAYS default to creating the new skill in the current project folder under .agents/skills (e.g., {proj-dir}/.agents/skills), unless the user explicitly mentions creating it in the ai-registry or globally. Always run the init_skill.ts script with Bun. 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.
When maintaining init_skill.ts, scaffold template content, or validator-adjacent code, first generate a fresh skill with init_skill.ts and immediately run quick_validate.ts against that untouched scaffold before making any manual edits. Treat that init-to-validate pass as the first regression check for scaffold/validator compatibility, because it catches frontmatter and template contract drift that hand-edited examples can hide.
Usage:
bun {{skills_dir}}/skill-writer/scripts/init_skill.ts <skill-name> --path .agents/skills
bun {{skills_dir}}/skill-writer/scripts/init_skill.ts <skill-name> --path {{skills_dir}}
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. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance 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: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a brand-guidelines skill, the user may need to provide brand assets or templates to store in assets/, or documentation to store in references/.
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 scripts/, references/, and assets/ to demonstrate structure, but most skills won't need all of them.
Update SKILL.md
Writing Guidelines: Always use imperative/infinitive form.
Self-review to 10/10
Do not stop at the first draft that seems acceptable. Self-review the skill against an explicit quality bar, correct weaknesses, and repeat until the result would reasonably score 10/10 against the rubric below.
Use a bounded review loop:
- Draft the smallest correct version of the skill.
- Review it critically against the rubric.
- Fix the highest-impact problems first.
- Repeat until every rubric item passes cleanly or an external constraint prevents further improvement.
Treat 10/10 as meaning the skill is clear, correctly scoped, concise, internally consistent, and ready for another agent to use without avoidable confusion. Do not chase perfection through meaningless rewrites; stop only when additional edits no longer improve correctness, clarity, triggering, or usability.
Review rubric:
- Triggering quality: Does the
description clearly say what the skill does, when to use it, and nearby cases that should not trigger it?
- Workflow quality: Are the steps concrete, ordered, and actionable instead of vague advice?
- Resource quality: Are scripts, references, and assets present only when they materially improve reliability or reuse?
- Conciseness: Is every section earning its token cost, with bulky details moved into references when appropriate?
- Consistency: Do frontmatter, body instructions, scripts, and examples agree with each other?
- Usability: Could another agent execute the skill successfully without guessing missing context?
Frontmatter
Write the YAML frontmatter with name, description, and author:
name: The skill namedescription: This is the primary triggering mechanism for your skill, and helps Claude understand when to use it.
- Keep it to 1-2 sentences focused on scope and triggers.
- Include what the skill does, the kinds of requests or artifacts that should trigger it, and optionally one nearby non-trigger boundary if that materially improves routing.
- Include all true trigger information here, not buried only in the body. The body is loaded after triggering.
- Do not put workflow rules, command requirements, validation criteria, or step-by-step instructions here. Words like "always", "never", "require", and long procedural clauses usually belong in the body.
- Narrow exception for project-specific addenda: when authoring a project-local companion skill named
<base-skill>-addendum, use the description to declare the dependency because current harnesses route skills from name and description. Use this exact pattern: If <base-skill> skill is used, this skill must be used as well.
- Keep that exception narrow. Do not make the base global skill describe project-local addenda, do not create multiple addenda for the same base skill in one project, and do not duplicate the global skill into the project just to add project-specific rules.
- Good example for a
docx skill: "Create, edit, and inspect .docx documents. Use when the task involves Word files, tracked changes, comments, or formatting-preserving document updates."
- Anti-pattern: "Create DOCX documents and always preserve tracked changes, require comment anchors before edits, and stop to ask for clarification if formatting intent is ambiguous." Those are usage instructions, not trigger metadata.
author: Use alexgorbatchev for skills maintained in this registry.
Default to name, description, and author.
If you need extra frontmatter for a specific distribution flow, verify first that the local validator accepts it. In this toolchain, the allowed extra keys beyond those are currently license, allowed-tools, and metadata.
Body
Write instructions for using the skill and its bundled resources.
For a project-local <base-skill>-addendum, keep the body focused on the project-specific delta from the base skill. State clearly that project-specific guidance in the addendum supersedes conflicting guidance from the base skill for that project, and avoid repeating unchanged parts of the base skill.
Step 5: Validating a Skill
Once development of the skill is complete, validate it. Run the validator explicitly with Bun.
These entrypoint scripts are Bun scripts. Invoke them as bun <script> ....
Quick validation:
bun {{skills_dir}}/skill-writer/scripts/quick_validate.ts <path/to/skill-folder>
If you changed scaffold generation or validator behavior, validate a freshly generated skill before validating a hand-edited one.
The script will report any validation errors and exit. Fix any validation errors and run the validation command again. The validation checks:
- YAML frontmatter format and required fields
- Skill naming conventions and directory structure
- Description completeness and quality
- File organization and resource references
When changing scaffold or validator contracts, keep an end-to-end regression that covers initSkill(...) followed by validateSkill(...) so the generated default scaffold remains valid without manual cleanup.
Step 6: Iterate
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
Iteration workflow:
- Use the skill on real tasks
- Notice struggles or inefficiencies
- Identify how SKILL.md or bundled resources should be updated
- Implement changes and test again
Step 7: Finalize
If the skill covers existing instructions in .github/instructions, identify any overlaps or redundancies and offer the user to update the instructions accordingly.
