MCP HubMCP Hub
← 返回技能列表

c-browser

daxaur
更新于 Yesterday
3 次查看
143
6
143
在 GitHub 上查看
测试browserautomationscrapingweb

关于

c-browser enables headless browser automation for navigating pages, interacting with elements, and extracting content through two CLI tools. It provides capabilities like clicking, form filling, screenshot capture, and web scraping using either agent-browser for structured snapshots or playwright-cli for token-efficient operations. Use this skill when you need to automate web interactions or collect data from websites within your development workflow.

快速安装

Claude Code

推荐
主要方式
npx skills add daxaur/openpaw -a claude-code
插件命令备选方式
/plugin add https://github.com/daxaur/openpaw
Git 克隆备选方式
git clone https://github.com/daxaur/openpaw.git ~/.claude/skills/c-browser

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Browser Automation

agent-browser (Vercel)

Navigate and interact with web pages using structured snapshots:

# Open a URL
agent-browser open "https://example.com"

# Get interactive element snapshot (shows clickable refs)
agent-browser snapshot -i

# Click an element by ref
agent-browser click @e2

# Fill a form field
agent-browser fill @e5 "search query"

# Take annotated screenshot
agent-browser screenshot --annotate

# Type text
agent-browser type "hello world"

# Press keys
agent-browser press Enter

playwright-cli (Microsoft)

Token-efficient browser automation designed for AI agents:

# Install browser (first time)
playwright-cli install-browser

# Navigate to URL
playwright-cli navigate "https://example.com"

# Get page snapshot
playwright-cli snapshot

# Click element
playwright-cli click "Submit button"

# Fill input
playwright-cli fill "Search" "query text"

# Screenshot
playwright-cli screenshot

Guidelines

  • Use agent-browser for AI-driven web interaction (snapshot-ref pattern)
  • Use playwright-cli for structured automation and testing flows
  • Always check snapshots before clicking — element refs change between pages
  • For login flows, navigate step by step and verify each page loads
  • Respect robots.txt and rate limits when scraping

GitHub 仓库

daxaur/openpaw
路径: skills/c-browser
0
ai-agentanthropicautomationclaudeclaude-codecli

相关推荐技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试（如MMLU、GSM8K等）评估大语言模型质量，适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口，被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能

cloudflare-cron-triggers

测试

这个Claude Skill提供了关于Cloudflare Cron Triggers的完整知识库，用于通过cron表达式定时执行Workers。它支持配置周期性任务、维护作业和自动化工作流，并能处理常见的cron触发错误。开发者可以用它来设置定时任务、测试cron处理器，并集成Workflows和Green Compute功能。

查看技能

webapp-testing

测试

该Skill为开发者提供了基于Playwright的本地Web应用测试工具集，支持自动化测试前端功能、调试UI行为、捕获屏幕截图和查看浏览器日志。它包含管理服务器生命周期的辅助脚本，可直接作为黑盒工具运行而无需阅读源码。适用于需要快速验证本地Web应用界面和交互功能的开发场景。

查看技能

finishing-a-development-branch

测试

这个Skill用于开发分支完成后的集成决策，当代码实现完成且测试通过时，它会引导开发者选择合适的工作流。它首先验证测试状态，然后提供合并、创建PR或清理等结构化选项。核心价值在于确保代码质量的同时，标准化分支收尾流程。

查看技能