create-skill（创造技能）

🎯 Onboarding Awareness (CHECK BEFORE STARTING)

Before creating a skill, AI MUST check stats.pending_onboarding for learn_skills:

Pre-Flight Check (MANDATORY)

Check if learn_skills is in stats.pending_onboarding. If present AND this is user's FIRST skill:

💡 Before creating your first skill, would you like a quick 10-minute tutorial
on what makes workflows "skill-worthy"? It covers:
- The 3-criteria skill-worthiness framework
- How skills are structured (SKILL.md, scripts/, references/)
- How AI triggers skills automatically

Say 'learn skills' to start the tutorial, or 'skip' to create directly.

If user says 'skip': Proceed with skill creation but add this note at the end:

💡 Tip: Run 'learn skills' later to understand the skill system deeply.

If learn_skills NOT in pending_onboarding: Proceed normally without suggestion.

Anti-Pattern Detection

If user is creating similar items (report-jan, report-feb, report-mar pattern):

💡 I notice you're creating similar items. This is a perfect use case for
a SKILL instead of multiple projects/files. Want to 'learn skills' first
to understand how to capture this as a reusable workflow?

Create Skill

This skill provides guidance for creating 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

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 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.

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).

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 that determine when Claude uses the skill
• Body (Markdown): Instructions and guidance for using the skill

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 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.

• 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
• 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:

1. Metadata (name + description) - Always in context (~100 words)
2. SKILL.md body - When skill triggers (<5k words)
3. 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 Creation Process

Skill creation involves these steps:

1. Initialize TodoWrite - Create task tracking for visibility
2. Understand the skill with concrete examples
3. Plan reusable skill contents (scripts, references, assets)
4. Initialize the skill (run init_skill.py)
5. Edit the skill (implement resources and write SKILL.md)
6. Package the skill (run package_skill.py)
7. Iterate based on real usage
8. Close session - Auto-trigger to save progress

Follow these steps in order, skipping only if there is a clear reason why they are not applicable.

Step 1: Initialize TodoWrite (MANDATORY)

BEFORE starting skill creation work, initialize TodoWrite to track progress and give user visibility:

TodoWrite with all workflow steps:
- Understand skill with concrete examples
- Plan reusable skill contents (scripts, references, assets)
- Initialize skill structure with init_skill.py
- Implement scripts and resources
- Write SKILL.md instructions
- Package skill with validation
- Test and iterate
- Close session to save progress

This creates transparency and allows progress tracking throughout the multi-step process.

Mark tasks complete as you finish each step. Update the todo list in real-time to show progress.

Step 2: 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.

First, check recent conversation (10-20 messages) for workflow patterns:

• Did the user just complete a multi-step process?
• Is there a repetitive task pattern evident?
• Did the user ask "how do I do X" and receive step-by-step guidance?

If a pattern is detected, offer: "I noticed you just [completed workflow]. Want to save this as a skill?" If the user confirms, use that workflow as the concrete example. If no pattern exists, continue below.

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.

Mark this todo complete before proceeding.

Step 2.5: Apply Mental Models (Proactive Offering)

After understanding the skill requirements, AI always loads the mental-models framework to review available thinking frameworks, then offers 2-3 relevant options to deepen skill design.

Pattern (Proactive Offering):

1. AI loads mental-models skill automatically after understanding requirements
2. AI reviews catalog to identify 2-3 relevant models for skill design
3. AI offers models with descriptive but efficient metadata (3-7 words)
4. User picks which models to apply (or none)
5. AI loads specific reference files for selected models
6. AI applies questions from selected models to refine skill design

Example Offer:

Now let's think through this skill design. I've reviewed the mental models catalog and recommend:

1. **First Principles** – Strip assumptions, find fundamental truths
   Best for: Novel skill workflows, challenging existing approaches

2. **Stakeholder Mapping** – Identify all affected parties and interests
   Best for: Skills with multiple user types or use cases

3. **Pre-Mortem** – Imagine failure modes before implementation
   Best for: Complex skills with potential failure points

Which approach sounds most useful for designing this skill? Or continue without structured analysis?

When to Offer:

• ✅ After understanding concrete examples (Step 2)
• ✅ Before planning reusable contents (Step 3)
• ✅ When skill design has complexity or unknowns
• ❌ Skip for simple, straightforward skills (user can decline)

Loading Pattern:

User picks: "First Principles + Pre-Mortem"

AI loads:
→ mental-models/references/cognitive-models.md (First Principles section)
→ mental-models/references/diagnostic-models.md (Pre-Mortem section)
→ Apply questions from both models to refine skill design

Benefits:

• ✅ Deeper analysis - Mental models surface edge cases and risks
• ✅ User choice - User decides if/when to apply structured thinking
• ✅ Efficient - Brief descriptions (3-7 words), progressive disclosure
• ✅ Quality - Better skill design through systematic thinking

See: mental-models framework for full catalog

Step 3: 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.

Suggest a skill name: Based on the workflow, suggest a hyphen-case name following conventions (verb-noun pattern preferred). Present: "I'd call this: {suggested-name}. Sound good?" User confirms or provides an alternative. See references/naming-guidelines.md for conventions.

Mark this todo complete before proceeding.

Step 4: 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.

Usage:

scripts/init_skill.py <skill-name> --path <output-directory>

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.

Mark this todo complete before proceeding.

Step 5: 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.

Frontmatter

Write the YAML frontmatter with name and description:

• name: The skill name
• description: Be specific about what the skill does and when to use it

- Be specific and include key terms - Include both what the Skill does and specific triggers/contexts for when to use it - Provide enough detail for selection - Claude uses this to choose from 100+ Skills, so be comprehensive, concise, and direct

Do not include any other fields in YAML frontmatter.

Body

Write instructions for using the skill and its bundled resources.

Mark this todo complete before proceeding.

Step 6: Packaging a Skill

Once development of the skill is complete, it must be packaged into a distributable.skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:

scripts/package_skill.py <path/to/skill-folder>

Optional output directory specification:

scripts/package_skill.py <path/to/skill-folder> ./dist

The packaging script will:

1. Validate the skill automatically, checking:

- YAML frontmatter format and required fields - Skill naming conventions and directory structure - Description completeness and quality - File organization and resource references

1. 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.

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.

Optional: Nexus-v3 Integration

If using Nexus-v3 framework: Skills placed in 03-skills/ (user) or 00-system/skills/ (system) auto-integrate. The framework's loader scans YAML metadata on startup—no manual registration needed. Skills work standalone or in Nexus without modification.

After successful packaging, the packaging script will check if the skill is ready for Notion export and display:

📤 SHARE WITH TEAM
Would you like to export this skill to Notion?
  → Makes skill discoverable by your team
  → Enables collaborative improvement
  → Recommended for production-ready skills

To export, say: 'export this skill to Notion'

Mark this todo complete before proceeding.

Step 6.5: Share to Team (Optional but Recommended)

After packaging your skill, consider sharing it with the team via Notion. This makes your work discoverable and enables collaborative improvement.

Benefits of sharing:

• Team members can discover and reuse your work
• Others can collaboratively improve the skill
• Builds a centralized company skills library
• Skills are stored with full.skill file (scripts, references, assets included)

To share:

Simply say "export this skill to Notion" or use the export-skill-to-notion skill directly.

What happens during export:

1. AI packages the skill (if not already packaged) into a.skill file
2. AI infers the Team (General/Solutions/Engineering/Sales) based on skill content
3. You confirm metadata before pushing:

- Skill Name - Description - Purpose - Team assignment - Integration tags - Owner (from user-config.yaml)

1. Skill uploads to Notion database with full.skill file attached (not just SKILL.md)
2. Teammates can discover it using query-notion-db and import using import-skill-to-nexus

The workflow looks like:

You: "Export this skill to Notion"

AI: Based on the skill's purpose, I suggest Team: "General"
    (This is a utility skill for [description])
    Is this correct? (yes/no)

You: "yes"

AI: 📤 Ready to push skill to Notion:
    Skill Name: my-skill
    Team: General
    Owner: Your Name
    File: my-skill.skill (includes scripts/, references/, assets/)

    Push to Notion? (yes/no)

You: "yes"

AI: ✅ Skill pushed to Notion!
    🔗 https://notion.so/...

Skip this step if:

• Skill is personal/experimental/not ready to share
• Contains sensitive or client-specific information
• Still in active development phase

Notion export validation:

The packaging script automatically checks Notion-readiness:

• ✅ Purpose section exists (used for Notion Purpose field)
• ✅ Description is specific (not generic)
• ✅ Integration tags detected (helps with Team inference)
• ⚠️ Warnings about missing elements (won't block export)

For more details:

• See export-skill-to-notion for export workflow
• See query-notion-db for browsing shared skills
• See import-skill-to-nexus for importing teammate skills

Mark this todo complete after deciding (share or skip).

Step 7: 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:

1. Use the skill on real tasks
2. Notice struggles or inefficiencies
3. Identify how SKILL.md or bundled resources should be updated
4. Implement changes and test again

Mark this todo complete when iteration is done.

Step 8: Trigger close-session (MANDATORY)

python 00-system/core/nexus-loader.py --skill close-session

Then execute close-session workflow per SKILL.md