技能列表

|

Browser automation with Steel CLI as the default runtime, plus a Python Playwright fallback for custom flows. Use when the user asks to open a JS-heavy site, capture live page content, take screenshots/PDFs, fill forms, reuse a named browser session, or debug login/CAPTCHA/browser workflows. Trigger examples: 'Use Steel to log into this site and extract the table' or 'Take a real-browser screenshot of this dashboard'. Capabilities: (1) Steel CLI session workflows, (2) stateless scrape/screenshot

Extracts and archives chatgpt.com and claude.ai share links to Markdown using Chrome CDP (e.g., ChatGPT or Claude conversations).

使用 Chrome DevTools MCP 协议远程控制 Chrome 浏览器执行网页任务。当用户说"打开网站"、"帮我搜索"、"点进去看看"、"查看详情"、"操作网页"、"打开 ChatGPT/Gemini"等任何需要浏览器自动化执行的任务时触发。支持网站导航、元素交互、表单填写、多步骤跳转、信息提取、SSRF 白名单配置等完整功能。

Browser tool health check and auto-repair. Automatically checks browser status before each use and diagnoses/fixes issues. Use when: (1) preparing to use browser tool for screenshots/automation; (2) browser snapshot/start times out; (3) CDP connection fails; (4) user mentions "browser timeout", "CDP disconnected", "浏览器超时", "browser 失效".

Browser automation skill for uploading files to web pages with flexible path specification. Use when Codex needs to: (1) Upload files to web forms, (2) Automate file selection dialogs, (3) Interact with file input elements via agent-browser CLI. Supports absolute paths, relative paths, environment variables, and workspace-relative paths.

Browser automation skill for uploading files to web pages with flexible path specification. Use when Codex needs to: (1) Upload files to web forms, (2) Automate file selection dialogs, (3) Interact with file input elements via agent-browser CLI. Supports absolute paths, relative paths, environment variables, and workspace-relative paths.

Record browser demo videos from a plain-language brief by turning the requested flow into a plan, driving the OpenClaw browser via CDP, encoding an MP4, writing the output into the workspace `media/` directory, and returning it with the MEDIA protocol. Use when the user wants a browser walkthrough, product demo, site recording, landing-page capture, hover/click/search flow recording, or asks to package browser recording into a reusable skill.

|

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. Supports remote Browserbase sessions with automatic CAPTCHA solving, anti-bot stealth mode, and residential proxies — ideal for scraping protected websites, bypassing bot detection, and interacting with JavaScript-heavy pages.

>

>