Claude Skills
CollectionsCompareWorkflowsNominate
Sign inSign up
© 2026 Curated Agent Skills·Learn more about Agent Skills
Back to repository

agent-browser

verified

This skill should be used when the user asks to "browse a website", "open a webpage", "interact with a page", "take a screenshot", "fill out a form", "click a button", "scrape content", "automate browser tasks", or needs to navigate and interact with web pages.

View on GitHub

Marketplace

linuxlewis-agent-skills

linuxlewis/claude-skills

Plugin

agent-browser

tools

Repository

linuxlewis/claude-skills

plugins/agent-browser/skills/agent-browser/SKILL.md

Last Verified

February 2, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/linuxlewis/claude-skills/blob/main/plugins/agent-browser/skills/agent-browser/SKILL.md -a claude-code --skill agent-browser

Installation paths:

Claude
.claude/skills/agent-browser/
Powered by add-skill CLI

Instructions

# Agent Browser Skill

Browser automation using the `agent-browser` CLI - a fast, headless browser automation tool for AI agents.

## Installation

```bash
npm install -g agent-browser
# or use with npx
npx agent-browser install
```

## Quick Start

```bash
# Navigate to a URL
agent-browser open https://example.com

# Get accessibility snapshot (shows refs like @e1, @e2)
agent-browser snapshot -i

# Click using ref from snapshot
agent-browser click @e2

# Type into an element
agent-browser fill @e3 "hello world"

# Take screenshot
agent-browser screenshot output.png
```

## Core Commands

### Navigation
```bash
agent-browser open <url>           # Navigate to URL
agent-browser back                 # Go back
agent-browser forward              # Go forward
agent-browser reload               # Reload page
```

### Interaction
```bash
agent-browser click <sel>          # Click element (or @ref)
agent-browser dblclick <sel>       # Double-click
agent-browser type <sel> <text>    # Type into element
agent-browser fill <sel> <text>    # Clear and fill
agent-browser press <key>          # Press key (Enter, Tab, Control+a)
agent-browser hover <sel>          # Hover element
agent-browser focus <sel>          # Focus element
agent-browser check <sel>          # Check checkbox
agent-browser uncheck <sel>        # Uncheck checkbox
agent-browser select <sel> <val>   # Select dropdown option
```

### Getting Information
```bash
agent-browser snapshot             # Accessibility tree with refs
agent-browser snapshot -i          # Interactive elements only
agent-browser snapshot -c          # Compact (no empty elements)
agent-browser get text <sel>       # Get element text
agent-browser get html <sel>       # Get element HTML
agent-browser get value <sel>      # Get input value
agent-browser get title            # Get page title
agent-browser get url              # Get current URL
```

### Capture
```bash
agent-browser screenshot [path]    # Take screenshot
agent-browser screenshot 

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
4704 chars