Provides guidance and structural principles for creating modular, self-contained skills to extend agent capabilities with specialized knowledge and tools.
- GitHub stars
- 1,703
- Files
- 4
- Last commit
- Nov 11, 2026
- License
- Apache-2.0
- Allowed tools
- —
What does the skill-creator skill do?
skill-creator provides guidance and structural principles for creating modular, self-contained skills to extend agent capabilities with specialized knowledge and tools.
Summary generated from the skill's SKILL.md.
About the skill-creator skill
Developers looking to expand agent capabilities with specialized knowledge or tool integrations can use this guide to build modular, self-contained skills. It provides the structural principles necessary to transform a general-purpose agent into a specialized one by providing procedural knowledge, workflows, and domain expertise. The guide outlines how to organize files into project-local or global directories, ensuring that skills remain efficient and easy to manage.
Users learn to implement a progressive disclosure design to protect the context window, which is treated as a shared public good. This involves using a required SKILL.md file for core instructions and optional bundled resources like scripts for deterministic tasks, references for documentation, and assets for output files. The instructions cover everything from naming conventions using hyphen-case to specific creation steps like initializing with Python scripts and validating the final product to ensure reliability.
What an agent can do with it
- 1Create a new specialized skillA developer can follow the structured creation process to build a new skill that adds specific workflows or tool integrations to an agent.
- 2Organize complex domain knowledgeYou can use the pattern of splitting detailed documentation into reference files to keep the main instruction file lean.
- 3Implement deterministic automationDevelopers can include executable code within a skill to handle repetitive or fragile operations that require high consistency.
- 4Manage context window efficiencyUse the progressive disclosure principle to ensure the agent only loads heavy documentation when it is actually needed.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the skill-creator skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the skill-creator skill in Claude Code
~/.claude/skills/skill-creator/SKILL.md
$ npx degit bubbuild/bub/src/skills/skill-creator ~/.claude/skills/skill-creatorInstall the skill-creator skill in Claude Code (project)
.claude/skills/skill-creator/SKILL.md
$ npx degit bubbuild/bub/src/skills/skill-creator .claude/skills/skill-creatorInstall the skill-creator skill in Codex
~/.agents/skills/skill-creator/SKILL.md
$ npx degit bubbuild/bub/src/skills/skill-creator ~/.agents/skills/skill-creatorInstall the skill-creator skill in Gemini CLI
~/.gemini/skills/skill-creator/SKILL.md
$ npx degit bubbuild/bub/src/skills/skill-creator ~/.gemini/skills/skill-creatorInstall the skill-creator skill in Claude.ai
npx degit bubbuild/bub/src/skills/skill-creator skill-creator && zip -r skill-creator.zip skill-creator # claude.ai → Customize → Skills → + → Create skill → Upload a skill → skill-creator.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablebubbuild/bub/src/skills/skill-creator is public and reachablegithub.com/bubbuild/bub/tree/HEAD/src/skills/skill-creator ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/bubbuild/bub/commits ↗Pass
- No download-and-run or credential theft in scripts2 scripts read; no download-and-run, remote eval, base64 execution or credential uploadPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/bubbuild/bub/blob/HEAD/src/skills/skill-creator/S ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/bubbuild/bub/blob/HEAD/src/skills/skill-creator/S ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/bubbuild/bub/blob/HEAD/src/skills/skill-creator/S ↗Finding
SKILL.md
View on GitHubSkill Creator
This skill provides guidance for creating effective skills.
About Skills
Skills are modular, self-contained folders that extend Bub's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Bub from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
Skill Location Policy
When creating a skill, place it in one of these two roots:
- Project-local:
$workspace/.agents/skills/<skill-name> - Global:
~/.agents/skills/<skill-name>(shared across workspaces)
Prefer project-local by default. Use global only when the user explicitly wants the skill available across multiple workspaces.
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 Bub needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Bub is already very smart. Only add context Bub doesn't already have. Challenge each piece of information: "Does Bub 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 Bub 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
nameanddescriptionfields. These are the only fields that Bub 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.pyfor PDF rotation tasks - Benefits: Token efficient, deterministic, may be executed without loading into context
- Note: Scripts may still need to be read by Bub for patching or environment-specific adjustments
References (references/)
Documentation and reference material intended to be loaded as needed into context to inform Bub's process and thinking.
- When to include: For documentation that Bub should reference while working
- Examples:
references/finance.mdfor financial schemas,references/mnda.mdfor company NDA template,references/policies.mdfor company policies,references/api_docs.mdfor API specifications - Use cases: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
- Benefits: Keeps SKILL.md lean, loaded only when Bub 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 Bub produces.
- When to include: When the skill needs files that will be used in the final output
- Examples:
assets/logo.pngfor brand assets,assets/slides.pptxfor PowerPoint templates,assets/frontend-template/for HTML/React boilerplate,assets/font.ttffor typography - Use cases: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
- Benefits: Separates output resources from documentation, enables Bub 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 Bub (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
Bub 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, Bub 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, Bub 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)
Bub 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 Bub 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
uv run ${SKILL_DIR}/scripts/init_skill.py) - Edit the skill (implement resources and write SKILL.md)
- Validate the skill (run
uv run ${SKILL_DIR}/scripts/quick_validate.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
- 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.pyscript 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.mdfile 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. In this case, continue to the next step.
When creating a new skill from scratch, always run uv run ${SKILL_DIR}/scripts/init_skill.py. 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:
uv run ${SKILL_DIR}/scripts/init_skill.py <skill-name> --path <output-directory> [--resources scripts,references,assets] [--examples]
Examples:
uv run ${SKILL_DIR}/scripts/init_skill.py my-skill --path "$workspace/.agent/skills"
uv run ${SKILL_DIR}/scripts/init_skill.py my-skill --path "$workspace/.agent/skills" --resources scripts,references
uv run ${SKILL_DIR}/scripts/init_skill.py my-skill --path "$workspace/.agent/skills" --resources scripts --examples
uv run ${SKILL_DIR}/scripts/init_skill.py my-skill --path "~/.agent/skills"
The script:
- Creates the skill directory at the specified path
- Generates a SKILL.md template with proper frontmatter and TODO placeholders
- Optionally creates resource directories based on
--resources - Optionally adds example files when
--examplesis 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 Bub to use. Include information that would be beneficial and non-obvious to Bub. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Bub 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
Writing Guidelines: Always use imperative/infinitive form.
Frontmatter
Write the YAML frontmatter with name and description:
name: The skill namedescription: This is the primary triggering mechanism for your skill, and helps Bub 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 Bub.
- Example description for a
docxskill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Bub 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.
Body
Write instructions for using the skill and its bundled resources.
Step 5: Validate the Skill
Once development of the skill is complete, validate the skill folder to catch basic issues early:
uv run ${SKILL_DIR}/scripts/quick_validate.py <path/to/skill-folder>
The validation script checks YAML frontmatter format, required fields, and naming rules. If validation fails, fix the reported issues and run the 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
- Implement changes and test again
Files in this skill
4skill-creator skill questions
How do I install the skill-creator skill in Claude Code?
Run npx degit bubbuild/bub/src/skills/skill-creator ~/.claude/skills/skill-creator. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the skill-creator skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
Where should I store my new skill?
You can place skills in a project-local directory at $workspace/.agents/skills/<skill-name> or globally at ~/.agents/skills/<skill-name>.
What are the required components of a skill?
Every skill must include a SKILL.md file containing YAML frontmatter metadata (name and description) and Markdown instructions.
How can I manage large amounts of documentation without bloating the context window?
Use the Progressive Disclosure Design Principle by keeping the SKILL.md body lean and moving detailed reference material into a separate 'references/' folder.