‹ 首页

browser-automation

@vibeeval · 收录于 1 周前 · 上游提交 1 个月前

AI browser automation - navigate, interact, extract, verify via browser-use MCP

场景网页自动化数据采集表单填写

适合你，如果需要让AI代替手动操作浏览器完成重复任务

/ 下载安装
browser-automation.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add vibeeval/vibecosystem/browser-automation
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- vibeeval/vibecosystem/browser-automation
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify vibeeval/vibecosystem/browser-automation
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
515GitHub stars
~496上下文体积 · 单文件
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · cea9462

Browser Automation

AI-powered browser automation via browser-use MCP server. Navigate web pages, fill forms, extract content, take screenshots, and verify deployments.

Setup

Add to ~/.mcp.json:

{
  "mcpServers": {
    "browser-use": {
      "command": "uvx",
      "args": ["browser-use", "--mcp"]
    }
  }
}

Restart Claude Code after adding.

Usage
Navigate & Extract
/browser-automation navigate https://docs.example.com
/browser-automation extract https://docs.example.com --format markdown
Form Interaction
/browser-automation fill https://app.example.com/login
  email: test@example.com
  password: [from env TEST_PASSWORD]
  submit: button[type=submit]
Deploy Verification
/browser-automation verify https://myapp.com
  - Check: homepage loads (< 3s)
  - Check: /api/health returns 200
  - Check: login page renders
  - Screenshot: homepage, login, dashboard
Screenshot
/browser-automation screenshot https://myapp.com --full-page
/browser-automation screenshot https://myapp.com --element "#hero-section"
Integration Points

| Trigger | How It Helps | |---------|-------------| | shipper deploys | Auto-verify live URL, take screenshots | | e2e-runner needs browser | Natural language browser tests | | oracle needs deep docs | Navigate multi-page documentation | | designer needs references | Capture UI patterns from live sites | | qa-engineer tests forms | Fill and submit forms, verify results | | growth analyzes competitors | Extract features, pricing, UX patterns |

MCP Tools Available

| Tool | Description | |------|-------------| | browser_navigate | Go to a URL | | browser_click | Click element by selector or text | | browser_type | Type into input field | | browser_screenshot | Capture page/element screenshot | | browser_extract | Extract page content as text/markdown | | browser_wait | Wait for element or condition | | browser_evaluate | Execute JavaScript in page context | | browser_scroll | Scroll page or element |

Rules
  • Max 1 request/second to same domain
  • Respect robots.txt
  • Never store credentials in output
  • Timeout: 30 seconds per page
  • Retry once on failure, then report error
  • Blur sensitive data in screenshots
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…