skill-creator

name	skill-creator
description	Guide for creating or updating Wisepen AIAsset Skills that extend Wisepen with specialized knowledge, workflows, bundled text references, or script assets. Use when users want to design a new Skill, revise an existing Skill, or save Skill content as a Wisepen draft.

Skill Creator

This skill provides guidance for creating effective skills.

About Skills

Skills are modular, self-contained folders that extend Wisepen's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Wisepen from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.

What Skills Provide

1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. 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 Wisepen needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

Default assumption: Wisepen is already very smart. Only add context Wisepen doesn't already have. Challenge each piece of information: "Does Wisepen 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 Wisepen as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

Protect Validation Integrity

During iteration, validate whether a skill works on realistic tasks or whether a suspected problem is real. Treat validation as an evaluation surface: the goal is to learn whether the skill generalizes, not whether the answer can be reconstructed from leaked context.

Prefer raw artifacts such as example prompts, outputs, diffs, logs, or traces. Give the minimum task-local context needed to perform the validation. Avoid passing the intended answer, suspected bug, intended fix, or prior conclusions unless the validation explicitly requires them.

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 Wisepen 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).

Wisepen AIAsset Drafts

Wisepen Skills are saved as AIAsset drafts through controlled tools, not by creating a local skill directory. Use create_skill_info for new Skills, get_skill_info to inspect existing Skills and obtain the current draft version, update_skill_info only when metadata must change, then use upload_skill_draft_asset once per text asset.

• New Skills require a display title, name, and description.
• Existing Skills require resource_id for inspection, and require resource_id, name, and description only when updating metadata.
• Upload each changed or new text file with path as the directory and name as the file name.
• Saving a draft never publishes the Skill. Unless a publishing tool is provided in the future, publication remains outside this workflow.

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 Wisepen for patching or environment-specific adjustments

References (references/)

Documentation and reference material intended to be loaded as needed into context to inform Wisepen's process and thinking.

• When to include: For documentation that Wisepen 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 Wisepen 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 Wisepen 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 Wisepen to use files without loading them into context
• Current save-tool limit: upload_skill_draft_asset supports text assets only. Binary assets such as images, fonts, or office templates require a separate workflow.

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:

1. Metadata (name + description) - Always in context (~100 words)
2. SKILL.md body - When skill triggers (<5k words)
3. Bundled resources - As needed by Wisepen (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

Wisepen 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, Wisepen 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, Wisepen 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)

Wisepen 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 Wisepen can see the full scope when previewing.

Skill Creation Process

Skill creation involves these steps:

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Create or update Wisepen Skill info
4. Edit the skill content and upload draft assets
5. Validate the skill with static checks and realistic examples
6. 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).
• Use the same slug consistently for the Skill name and draft metadata.

Skill Structure Patterns

Choose the structure that best fits the skill's purpose. Patterns can be mixed when the skill needs more than one shape.

Workflow-Based is best for sequential processes with clear steps. Use a structure like Overview -> Workflow Decision Tree -> Step 1 -> Step 2.

Task-Based is best for tool collections or separate operations. Use a structure like Overview -> Quick Start -> Task Category 1 -> Task Category 2.

Reference/Guidelines is best for standards, specifications, brand guidance, coding rules, or requirements. Use a structure like Overview -> Guidelines -> Specifications -> Usage.

Capabilities-Based is best for integrated systems with multiple related features. Use a structure like Overview -> Core Capabilities -> numbered capability sections.

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?"
• "Is this a new Wisepen Skill, or should I update an existing Skill resource_id?"

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:

1. Considering how to execute on the example from scratch
2. 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:

1. Rotating a PDF requires re-writing the same code each time
2. 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:

1. Writing a frontend webapp requires the same boilerplate HTML/React each time
2. 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:

1. Querying BigQuery requires re-discovering the table schemas and relationships each time
2. 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: Create, Read, or Update Wisepen Skill Info

At this point, create a new Wisepen Skill info record, inspect an existing one, or update existing metadata only when it actually changed.

Skip this step only when the current turn is purely planning and the user has not asked to save a draft.

Use create_skill_info for a new Skill:

• Provide title, name, and description.
• Keep name and description aligned with /SKILL.md frontmatter.
• Record the returned resource_id and draft_version; every asset upload for this draft needs both values.

Use get_skill_info for an existing Skill:

• Provide resource_id.
• Read the returned resource_id, name, description, source_type, version, and draft_version.
• Use the returned draft_version for asset uploads.

Use update_skill_info only when existing metadata must change:

• Provide resource_id, name, and description.
• Keep name and description aligned with /SKILL.md frontmatter.
• If the next step needs a current draft_version, call get_skill_info after updating.

These tools only create, read, or update Skill information. They do not upload files and never publish.

Step 4: Edit the Skill and Upload Draft Assets

When editing the new or existing skill, remember that the skill is being created for another instance of Wisepen to use. Include information that would be beneficial and non-obvious to Wisepen. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Wisepen instance execute these tasks more effectively.

Start with Reusable Skill Contents

To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Prepare each resource as a POSIX directory path, file name, and text content. 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 should be written so they can be run and tested by the eventual Skill user. If local execution is available during Skill creation, run representative scripts to ensure there are no obvious bugs and that outputs match expectations.

Only include resource files 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 name
• description: This is the primary triggering mechanism for your skill, and helps Wisepen 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 Wisepen.
  • 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 Wisepen 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.

Upload Draft Assets

Use upload_skill_draft_asset once per file:

• To modify an existing draft file, upload the updated content for that file; to add a draft file, upload the new file content.
• Pass path and name separately, such as path="/", name="SKILL.md", path="/references", name="schema.md", or path="/scripts", name="rotate_pdf.py".
• Supported text asset extensions are .md, .py, .txt, .json, .yaml, .yml, and .toml.
• path must be / or an absolute POSIX directory path such as /references; name must be a file name only, not a path, and must not be . or ...
• Upload one file per tool call. Do not batch multiple files into a single call.

The tool does light /SKILL.md structure checks and validates asset path/name before uploading. It saves draft assets only and never publishes.

Step 5: Validate the Skill

Once development of the skill is complete, validate the draft content to catch basic issues early:

• Confirm /SKILL.md starts with YAML frontmatter containing only name and description.
• Confirm name is lowercase hyphen-case and matches the metadata saved with create_skill_info or update_skill_info.
• Confirm description includes both what the Skill does and specific triggers or contexts for when to use it.
• Confirm the body is non-empty, concise, and points to any references or scripts by exact path/name.
• Confirm every referenced bundled resource was uploaded with upload_skill_draft_asset.
• If scripts are included and execution is possible in the current environment, run a representative sample.

Step 6: Iterate

After testing the skill, you may detect that it needs clearer instructions, more focused references, or fewer resources; or users may request improvements.

User testing often this happens right after using the skill, with fresh context of how the skill performed.

Iteration workflow:

1. Use the skill on real tasks
2. Notice struggles or inefficiencies
3. Identify how SKILL.md or bundled resources should be updated
4. Use update_skill_info if name or description changed
5. Re-upload changed assets one file at a time
6. Validate again with realistic prompts and raw artifacts

When validating, pass the skill and a request in a similar way the user would. Prefer raw artifacts over conclusions, avoid showing expected answers or intended fixes, and rebuild context from source artifacts after each iteration.