Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.
Skill Creator
This skill provides guidance for creating effective skills.
About Skills
Skills are modular, self-contained packages that extend Codex's capabilities by providing
specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
domains or tasks—they transform Codex 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
Skill-First Capability Design
Prefer a skill when the user wants the agent to keep a reusable capability
instead of only completing the current turn. A skill is the durable form for
user-taught behavior: it stores when the capability should trigger, how to use
it, what constraints matter, how to recover from common failures, and which
resources make execution reliable.
Create or update a skill when the user asks to:
add, remember, teach, configure, preserve, or reuse a capability
connect to a tool, API, CLI, MCP endpoint, internal service, or workflow
encode a team process, domain rule, document convention, or review checklist
make future tasks follow a pattern instead of repeating instructions manually
restrict use by natural-language conditions such as requester, team, chat,
project, environment, or business context
Do not create a skill for one-off work that is unlikely to repeat. Finish the
task directly when the user only needs a single answer, file, edit, or command
result and there is no durable workflow to preserve.
Use memory instead of a skill for lightweight facts, preferences, and simple
standing rules that do not need an executable workflow, tools, references,
examples, or recovery paths. Use a skill when the remembered item is an
operational capability that future tasks should be able to run.
Keep the boundary clear:
Put stable platform invariants in application code or runtime config:
permissions, secret storage, file access, execution safety, validation, and
lifecycle management.
Put evolving behavior in the skill: triggers, operating steps, domain
knowledge, examples, recovery paths, and policy-like usage constraints.
Put deterministic, fragile, or frequently repeated operations in scripts.
Put long schemas, API docs, and detailed procedures in references.
Put reusable templates or media in assets.
Natural-language constraints in a skill guide model behavior; they are not a
hard security boundary. Do not rely on a skill description alone to protect
secrets, permissions, or private data.
Core Principles
Concise is Key
The context window is a public good. Skills share the context window with everything else Codex needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Codex is already very smart. Only add context Codex doesn't already have. Challenge each piece of information: "Does Codex 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 Codex as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Anatomy of a Skill
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
SKILL.md (required)
Every SKILL.md consists of:
Frontmatter (YAML): Contains name and description fields. These are the only fields that Codex reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
Body (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).
Bundled Resources (optional)
Scripts (scripts/)
Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
When to include: When the same code is being rewritten repeatedly or deterministic reliability is needed
Example: scripts/rotate_pdf.py for PDF rotation tasks
Benefits: Token efficient, deterministic, may be executed without loading into context
Note: Scripts may still need to be read by Codex for patching or environment-specific adjustments
References (references/)
Documentation and reference material intended to be loaded as needed into context to inform Codex's process and thinking.
When to include: For documentation that Codex 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
Benefits: Keeps SKILL.md lean, loaded only when Codex 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 Codex 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 Codex 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 Codex (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
Codex 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 the user chooses AWS, Codex 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)
Codex 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 Codex 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 (run init_skill.py)
Edit the skill (implement resources and write SKILL.md)
Package the skill (run package_skill.py)
Iterate based on real usage
Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
Skill Naming
Use lowercase letters, digits, and hyphens only; normalize user-provided titles to hyphen-case (e.g., "Plan Mode" -> plan-mode).
When generating names, generate a name under 64 characters (letters, digits, hyphens).
Prefer short, verb-led phrases that describe the action.
Namespace by tool when it improves clarity or triggering (e.g., gh-address-comments, linear-address-issue).
Name the skill folder exactly after the skill name.
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
Deciding which parts are durable behavior and which parts need platform or runtime safeguards
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
Example: When building an internal-docs skill around a docs API, CLI, or MCP server, the analysis shows:
The durable capability is knowing when to use the docs system, how to search, how to read, and how to publish safely
Authentication, secret storage, network access, and execution limits belong to the surrounding platform or runtime config
A concise SKILL.md, optional references/usage.md, and a small script or MCP config would be helpful to store in the skill
To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
Step 3: Initializing the Skill
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
When creating a new skill from scratch, always run the init_skill.py script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
Generates a SKILL.md template with proper frontmatter and TODO placeholders
Optionally creates resource directories based on --resources
Optionally adds example files when --examples is set
After initialization, customize the SKILL.md and add resources as needed. If you used --examples, replace or delete placeholder files.
Step 4: Edit the Skill
When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Codex to use. Include information that would be beneficial and non-obvious to Codex. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Codex 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.
If you used --examples, delete any placeholder files that are not needed for the skill. Only create resource directories that are actually required.
Update SKILL.md
Write SKILL.md as the operating contract for the durable capability. It should explain when the capability applies, the smallest reliable workflow for using it, the important constraints, and the recovery paths that keep future runs moving.
For tool, API, CLI, or MCP integrations, keep the skill as the user-facing capability boundary. Put the invocation recipe, schema lookup command, examples, and domain-specific constraints in the skill. Keep shared, bundled, published, or repo-tracked skills free of raw secrets; reference environment variables, runtime config, auth helpers, or platform-managed credentials instead.
If the user explicitly provides a complete private config or credential-bearing endpoint for a local runtime capability, store it in a local private config file such as skill-local mcp.json in a writable user-managed skill root, or another dedicated private config path, rather than asking the user to re-enter the same value as an environment variable. Keep that file non-shared, excluded from source control and packaging, and outside repo-tracked skill artifacts. Use restrictive file permissions when possible, do not edit shell startup or trusted env files just to persist it, do not echo secret values back, and keep the skill instructions focused on when and how to use that config.
When the user asks for a capability with contextual limits such as "only for this team", "only in this project", "only when I ask", or "only for these chats", capture those limits in clear natural language in the skill. Treat these limits as behavioral guidance for the model, not as a hard security boundary.
Writing Guidelines: Always use imperative/infinitive form.
Frontmatter
Write the YAML frontmatter with name and description:
name: The skill name
description: This is the primary triggering mechanism for your skill, and helps Codex 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 Codex.
Example description for a docx skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Codex 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"
Keep generic skills to name and description unless the target runtime
already supports additional fields such as license, allowed-tools,
metadata, homepage, or user-invocable.
Body
Write instructions for using the skill and its bundled resources.
Step 5: Packaging a Skill
Validate every new or modified package-format skill. Do not bulk-force this
validator across legacy bundled OpenClaw skills that intentionally use a
runtime-specific or non-packaged format; inspect or test those with the
runtime's own workflow. Package a skill into a distributable .skill file only
when the user asks for a shareable artifact, the skill needs to be installed
elsewhere, or the runtime expects a packaged skill. For local durable
capabilities, keep the skill in the writable skill root, refresh or reload
skills when the runtime provides that path, and use it for the current task.
The packaging process automatically validates the skill first to ensure it
meets all requirements:
Package the skill if validation passes, creating a .skill file named after the skill (e.g., my-skill.skill) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
Security restriction: symlinks are rejected and packaging fails when any symlink is present.
If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
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
