Claude Skill

browser

Web browser control.

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download dhaupin-vant-models_public_vant_skills_vant-skill-browser-e1e348e.zip · 0 KB

Install

skills CLI npx skills add https://github.com/dhaupin/vant/tree/main/models/public/vant/skills/vant-skill-browser
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install dhaupin-vant@llmmart
Git git clone https://github.com/dhaupin/vant.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole dhaupin/vant collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Browser Automation

Web browser control.


When To Use

  • Web interaction required
  • JavaScript rendering
  • UI testing

What To Do

1. Navigation

browser_navigate url="https://..."

2. Interaction

Action Tool
Click browser_click
Type browser_type
Scroll browser_scroll
Get content browser_get_content

3. Extract Data

// Get page content
browser_get_content()

// Get screenshot
browser_get_state(include_screenshot=true)

4. Wait for JS

# Pages render dynamically
# Use browser_get_state after navigate

Output

## Browser Automation

| Action | Result |
|--------|--------|
| Navigate | [URL] |
| Click | [element] |
| Extract | [data] |

### Screenshots
- [count]

Role: Browser Automator Input: URLs Output: Extracted data

Web at your command.

Files (vant)
  • SKILL.md 1 KB
    ---
    name: browser
    description: Web browser control.
    license: MIT
    metadata:
      author: vant
      version: "1.0"
    ---
    
    # Browser Automation
    
    > Web browser control.
    
    ---
    
    ## When To Use
    
    - Web interaction required
    - JavaScript rendering
    - UI testing
    
    ---
    
    ## What To Do
    
    ### 1. Navigation
    
    ```bash
    browser_navigate url="https://..."
    ```
    
    ### 2. Interaction
    
    | Action | Tool |
    |--------|------|
    | Click | browser_click |
    | Type | browser_type |
    | Scroll | browser_scroll |
    | Get content | browser_get_content |
    
    ### 3. Extract Data
    
    ```javascript
    // Get page content
    browser_get_content()
    
    // Get screenshot
    browser_get_state(include_screenshot=true)
    ```
    
    ### 4. Wait for JS
    
    ```bash
    # Pages render dynamically
    # Use browser_get_state after navigate
    ```
    
    ---
    
    ## Output
    
    ```
    ## Browser Automation
    
    | Action | Result |
    |--------|--------|
    | Navigate | [URL] |
    | Click | [element] |
    | Extract | [data] |
    
    ### Screenshots
    - [count]
    ```
    
    ---
    
    **Role**: Browser Automator **Input**: URLs **Output**: Extracted data
    
    > Web at your command.

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.