智能浏览器
Agent Browser Skill
by baiyunrei2025
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/baiyunrei2025/agent-browser-skill文档
Description
Enhanced browser automation for OpenClaw agents with advanced navigation, screenshot, and interaction capabilities.
When to Use
Use this skill when:
- Automating web browsing tasks
- Taking screenshots of web pages
- Filling forms and clicking buttons
- Extracting data from websites
- Testing web applications
- Navigating complex web flows
Prerequisites
- OpenClaw browser tool must be enabled
- Chrome or Chromium browser installed
- Internet connection for web access
Examples
Basic Navigation
bash
# Navigate to a website
openclaw browser open --url "https://example.com"
# Take a screenshot
openclaw browser snapshot --url "https://example.com" --output screenshot.png
Form Interaction
bash
# Fill a form
openclaw browser act --url "https://forms.example.com" --kind fill --fields '{"name": "John", "email": "john@example.com"}'
# Click a button
openclaw browser act --url "https://example.com" --kind click --selector "button.submit"
Data Extraction
bash
# Extract page content
openclaw browser snapshot --url "https://news.example.com" --maxChars 5000
# Monitor page changes
openclaw browser act --url "https://status.example.com" --kind wait --textGone "Loading..."
Integration with OpenClaw
This skill enhances the native OpenClaw browser tool with:
- Simplified commands - Easier syntax for common tasks
- Error handling - Better recovery from failures
- Performance optimization - Faster page loads and interactions
- Accessibility support - Better element detection
Safety Notes
- Only automate public websites
- Respect robots.txt and terms of service
- Avoid excessive requests to prevent IP blocking
- Use delays between actions to mimic human behavior
Troubleshooting
Common Issues
- Browser not starting: Check if Chrome is installed
- Element not found: Try different selectors or wait for page load
- Timeout errors: Increase timeout values for slow pages
- Permission denied: Ensure OpenClaw has necessary permissions
Debug Tips
bash
# Enable verbose logging
openclaw browser open --url "https://example.com" --verbose
# Check browser status
openclaw browser status
References
相关 MCP 服务
Puppeteer 浏览器控制
编辑精选by Anthropic
Puppeteer 是让 Claude 自动操作浏览器进行网页抓取和测试的 MCP 服务器。
✎ 这个服务器解决了手动编写 Puppeteer 脚本的繁琐问题,适合需要自动化网页交互的开发者,比如抓取动态内容或做端到端测试。不过,作为参考实现,它可能缺少生产级的安全防护,建议在可控环境中使用。
搜索与获取
86.1kBrave 搜索
编辑精选by Anthropic
Brave Search 是让 Claude 直接调用 Brave 搜索 API 获取实时网络信息的 MCP 服务器。
✎ 如果你想让 AI 助手帮你搜索最新资讯或技术文档,这个工具能绕过传统搜索的限制,直接返回结构化数据。特别适合需要实时信息的开发者,比如查 API 更新或竞品动态。不过它依赖 Brave 的 API 配额,高频使用可能受限。
搜索与获取
86.1k网页抓取
编辑精选by Anthropic
Fetch 是 MCP 官方参考服务器,让 AI 能抓取网页并转为 Markdown 格式。
✎ 这个服务器解决了 AI 直接处理网页内容时格式混乱的问题,适合需要让 Claude 分析在线文档或新闻的开发者。不过作为参考实现,它缺乏生产级的安全配置,你得自己处理反爬虫和隐私风险。
搜索与获取
86.1k