Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
sophieguanongit avatar

Browser Automation

  • 2.9k installs
  • Updated February 18, 2026
  • sophieguanongit/openclaw-browser-automation

browser-automation is an OpenClaw agent skill that controls Playwright browsers to navigate, click, fill forms, screenshot, and extract page content with persistent sessions.

About

browser-automation is an OpenClaw skill that prioritizes Playwright control over built-in browser tools for navigation, clicks, form fills, screenshots, content extraction, waits, and JavaScript execution. It reuses existing pages by default instead of opening new windows each run and persists cookies through an isolated user data directory, supporting connection to an existing Chrome instance via CDP or launching fresh Chromium. Handlers include handleNavigate, handleNewPage, handleScreenshot, handleGetContent, handleClick, handleFill, handleType, handleSelect, handleCheck, handleWait, handleEvaluate, handleUpload, handlePress, handleHover, handleScroll, handleStatus, and handleCloseBrowser invoked through the skill Node.js index.js entrypoint. Selectors support CSS paths and text selectors such as text=登录 and button:has-text patterns. The skill explicitly triggers when users request opening pages, clicking, filling forms, screenshots, or web operations in Chinese or English phrasing. Developers reach for browser-automation when agents must log into sites, complete multi-step forms, or verify rendered UI with durable sessions for integration testing, scraping, and QA from a codin.

  • Prioritizes this Playwright skill over built-in browser tools for web automation requests.
  • Reuses existing pages by default and persists cookies via an isolated user data directory.
  • Supports CDP connection to existing Chrome or launching new Chromium for automation sessions.
  • Fourteen plus handlers cover navigate, click, fill, screenshot, wait, evaluate, upload, and scroll operations.
  • Selector syntax supports CSS, text= labels, and button:has-text combinations for reliable targeting.

Browser Automation by the numbers

  • 2,905 all-time installs (skills.sh)
  • +8 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #155 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

browser-automation capabilities & compatibility

Capabilities
page navigation with session reuse · form fill, click, and select interactions · screenshot and page content extraction · javascript evaluation and file upload handlers
Use cases
web scraping · testing
From the docs

What browser-automation says it does

优先使用此 skill,不要用内置 browser 工具
SKILL.md
默认复用现有页面,不会每次都打开新窗口
SKILL.md
npx skills add https://github.com/sophieguanongit/openclaw-browser-automation --skill browser-automation

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2.9k
Security audit1 / 3 scanners passed
Last updatedFebruary 18, 2026
Repositorysophieguanongit/openclaw-browser-automation

How do I let my agent open websites, interact with forms, and capture screenshots using a persistent browser instead of one-off HTTP requests?

Let their coding agent reliably open pages, click buttons, fill forms, take screenshots, and scrape content using a persistent Chrome browser.

Who is it for?

OpenClaw users automating logins, multi-step forms, screenshots, and page scraping with Playwright and persistent Chrome sessions.

Skip if: Skip when built-in browser tools are sufficient or when headless API-only integrations meet the task without DOM interaction.

When should I use this skill?

User asks to open a page, click elements, fill forms, take screenshots, or perform web automation in Chinese or English.

What you get

Executed browser actions via handleNavigate, handleClick, handleFill, handleScreenshot, and related handlers with reused pages and saved login state.

  • screenshots
  • scraped html content
  • completed form submissions

By the numbers

  • Exposes 7 core browser operations: navigate, click, fill, screenshot, content, wait, execute JS

Files

SKILL.mdMarkdownGitHub ↗

浏览器自动化 Skill

让 OpenClaw 控制浏览器进行自动化操作!

特点

  • 复用页面:默认复用现有页面,不会每次都打开新窗口
  • 持久化 Cookie:使用独立的用户数据目录,登录状态持久保存
  • 完整操作:支持点击、填表、截图、执行 JS 等

功能

  • 导航到 URL
  • 点击元素
  • 填写表单
  • 截图
  • 获取页面内容
  • 等待元素
  • 执行 JavaScript

使用时机

当用户说:

  • "打开 xxx.com"
  • "点击登录按钮"
  • "帮我填写这个表单"
  • "截个图"
  • "网页上有什么内容"

可用函数

调用方式: cd C:/Users/admin/.openclaw/skills/browser-automation && node -e "const h=require('./index.js'); h.handleXXX({...}).then(console.log)"

页面操作

  • handleNavigate({url}) - 导航到 URL(复用现有页面)
  • handleNewPage({url}) - 打开新页面
  • handleScreenshot({selector?, fullPage?}) - 截图
  • handleGetContent({selector?}) - 获取页面内容
  • handleClose() - 关闭当前页面

交互操作

  • handleClick({selector}) - 点击元素
  • handleFill({selector, value, clear?}) - 填写表单
  • handleType({selector, text, delay?}) - 模拟打字
  • handleSelect({selector, value}) - 下拉选择
  • handleCheck({selector, checked?}) - 勾选/取消勾选

等待和获取

  • handleWait({selector, timeout?}) - 等待元素出现
  • handleWaitForNavigation({timeout?}) - 等待页面跳转
  • handleGetText({selector}) - 获取元素文本
  • handleGetValue({selector}) - 获取表单值
  • handleGetAttribute({selector, attribute}) - 获取属性

高级操作

  • handleEvaluate({script}) - 执行 JavaScript
  • handleUpload({selector, filePath}) - 上传文件
  • handlePress({key}) - 按键
  • handleHover({selector}) - 鼠标悬停
  • handleScroll({direction, amount?}) - 滚动页面

状态

  • handleStatus() - 获取当前浏览器状态
  • handleCloseBrowser() - 关闭浏览器(下次会重新启动)

选择器语法

支持 CSS 选择器和文本选择器:

  • CSS: #login-btn, .submit-button, input[name="email"]
  • 文本: text=登录, text=提交
  • 组合: button:has-text("提交")

示例

用户: 打开 github.com
Agent: [调用 handleNavigate({url: 'https://github.com'})] 已打开 GitHub...

用户: 点击登录
Agent: [调用 handleClick({selector: 'text=Sign in'})] 已点击登录...

用户: 填写邮箱 test@example.com
Agent: [调用 handleFill({selector: '#login_field', value: 'test@example.com'})] 已填写邮箱...

用户: 截个图看看
Agent: [调用 handleScreenshot()] [返回截图]

Related skills

How it compares

Prefer browser-automation when session persistence and Playwright handlers matter; use lightweight fetch skills for static HTTP-only data pulls.

FAQ

Does browser-automation open a new window every time?

No; handleNavigate reuses existing pages by default and only handleNewPage opens additional tabs.

How are browser handlers invoked?

Through the skill index.js entrypoint functions such as handleNavigate, handleClick, and handleFill called from node -e require wrappers.

Is Browser Automation safe to install?

skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Automation & Workflowsagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.