Skill Creator For Work

---
name: skill-creator-for-work
description: 创建有效 Skill 的指南。当用户想要创建新的 Skill，或更新现有 Skill，以便通过专门知识、工作流程或工具集成来扩展 AI Agent 能力时，应使用此 Skill。
license: Complete terms in LICENSE.txt
---

# Skill Creator

This skill provides guidance for creating effective skills.

## About Skills

Skills are modular, self-contained folders that extend the AI agent's capabilities by providing
specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
domains or tasks—they transform a general-purpose AI 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 the AI agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

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

### Default Skill Creation Location

Unless the user explicitly specifies a different location, every Skill created with this Skill must be created inside an existing directory whose path ends with `workspace/.user_skills`.

Do not assume that this directory is always exactly `~/workspace/.user_skills`. The path before `workspace/.user_skills` may vary across operating systems and runtime environments. Determine the correct directory from the Skill paths already known in the current environment: inspect those paths and their surrounding roots, locate the existing `workspace/.user_skills` directory associated with the active environment, and use it as the output directory. The resulting Skill path must have this form:

```text
<environment-specific-parent>/workspace/.user_skills/<skill-name>
```

Follow these rules whenever selecting or mentioning a Skill creation location:

1. Use another location only when the user explicitly requests it.
2. Otherwise, resolve and use the existing directory ending in `workspace/.user_skills`; do not fall back to the current working directory, `~/.codex/skills`, `.agents/skills`, or another convenient path.
3. When multiple matching directories exist, use the one associated with the currently known Skill directory and active environment.
4. Do not ask the user to confirm the default location when it can be resolved from known Skill paths. If no matching directory can be identified unambiguously, ask the user for the correct location instead of inventing one.

### Default to Browser Use for Website Content Collection

When creating a skill for collecting information from a website or web app, make Browser Use the default execution path. This includes tasks such as searching, browsing feeds, opening posts, reading comments, collecting user feedback, checking product mentions, or gathering visible page content from sites such as Xiaohongshu/RED, social platforms, forums, documentation sites, dashboards, or SaaS web apps.

Do not frame these tasks as Python crawler, scraper, or website API implementation tasks by default. The agent environment that will run the generated skill supports browser operation, so the skill should instruct the agent to use Browser Use to navigate, search, click, scroll, inspect pages, and extract visible content.

Only create Python crawler scripts, scraping scripts, or undocumented website API integrations when the user explicitly asks for a crawler/API-based skill, or when browser operation is insufficient for a clearly stated requirement. Python scripts may still be appropriate for deterministic post-processing of browser-collected data, such as deduplication, classification, formatting, or report generation.

### 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 the AI agent 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 the AI agent for patching or environment-specific adjustments

##### References (`references/`)

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

- **When to include**: For documentation that the AI agent 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 the AI agent 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 the AI agent 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 the AI agent 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 the AI agent (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**

```markdown
# 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
```

the AI agent 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, the AI agent 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, the AI agent only reads aws.md.

**Pattern 3: Conditional details**

Show basic content, link to advanced content:

```markdown
# 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)
```

the AI agent 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 the AI agent 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. Resolve the required `workspace/.user_skills` directory and initialize the skill there (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Finalize the skill folder
6. 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:

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

For website content collection skills, follow the "Default to Browser Use for Website Content Collection" principle above while planning resources. Usually this means writing a Browser Use workflow in `SKILL.md` and adding optional post-processing scripts only after the browser collection path is clear.

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 only needs iteration. In this case, continue to the next step.

Before initializing a new Skill, apply the "Default Skill Creation Location" rules above. Unless the user explicitly provided another location, locate the existing directory ending in `workspace/.user_skills` from the Skill paths known in the current environment and pass that directory to `--path`. Do not assume a fixed parent before `workspace`, because that parent is environment-specific.

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:

```bash
scripts/init_skill.py <skill-name> --path <existing-workspace/.user_skills-directory>
```

With the default location rule, `--path` receives the resolved `workspace/.user_skills` directory, and the script creates `<skill-name>` directly inside it. Only pass a different output directory when the user explicitly requested that directory.

The script:

- Creates the skill directory inside the resolved `workspace/.user_skills` directory, or inside the alternate directory explicitly requested by the user
- 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 AI agent instance to use. Include information that would be beneficial and non-obvious to that agent. Consider what procedural knowledge, domain-specific details, or reusable assets would help it 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`: This is the primary triggering mechanism for your skill, and helps the AI agent 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 the AI agent.
  - 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 the AI agent 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: Finalize the Skill Folder

Once development of the skill is complete, keep the skill as a normal folder. Do not create a zip archive and do not create a `.skill` file.

Before considering the work complete:

1. Confirm the folder contains the required `SKILL.md` file.
2. Confirm any needed `scripts/`, `references/`, and `assets/` files are present.
3. Delete placeholder files, unused example resources, caches, and temporary output.
4. Run any included scripts that need testing, or explain why they were not run.
5. If `scripts/quick_validate.py` is available, run it against the skill folder to check the frontmatter and naming basics:

```bash
scripts/quick_validate.py <resolved-workspace/.user_skills-directory>/<skill-name>
```

The finalized skill folder itself is the deliverable. Unless the user explicitly requested another location, leave it in the resolved `workspace/.user_skills` directory and preserve the complete directory structure so it can be loaded as a folder.

### 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:**

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