Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install browser-automation或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install browser-automation⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/browser-automation/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: browser description: Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. allowed-tools: Bash ---
Automate browser interactions using Stagehand CLI with Claude.
The skill automatically selects between local and remote browser environments:
Check setup.json in this directory. If setupComplete: false:
npm install # Install dependencies
npm link # Create global 'browser' command
All commands work identically in both modes:
browser navigate <url> # Go to URL
browser act "<action>" # Natural language action
browser extract "<instruction>" ['{}'] # Extract data (optional schema)
browser observe "<query>" # Discover elements
browser screenshot # Take screenshot
browser close # Close browser
browser navigate https://example.com
browser act "click the Sign In button"
browser extract "get the page title"
browser close
| Feature | Local | Browserbase | |---------|-------|-------------| | Speed | Faster | Slightly slower | | Setup | Chrome required | API key required | | Stealth mode | No | Yes | | Proxy/CAPTCHA | No | Yes | | Best for | Development | Production/scraping |
browser observe to discover available elementsFor detailed examples, see EXAMPLES.md. For API reference, see REFERENCE.md.
安装 Browser Automation 后,可以对 AI 说这些话来触发它
Help me get started with Browser Automation
Explains what Browser Automation does, walks through the setup, and runs a quick demo based on your current project
Use Browser Automation to automate web browser interactions using natural language via CLI co...
Invokes Browser Automation with the right parameters and returns the result directly in the conversation
What can I do with Browser Automation in my developer & devops workflow?
Lists the top use cases for Browser Automation, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/browser-automation/ 目录(个人级,所有项目可用),或 .claude/skills/browser-automation/(项目级)。重启 AI 客户端后,用 /browser-automation 主动调用,或让 AI 根据上下文自动发现并使用。
Browser Automation 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Browser Automation 可免费安装使用。请查阅仓库了解许可证信息。
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Browser Automation 属于「Developer & DevOps」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my developer & devops tasks using Browser Automation
Identifies repetitive steps in your workflow and sets up Browser Automation to handle them automatically