browser-use-zh

browser-use-zh is a skill for Claude Code from L-LesterYu/OpenClaw-hot-skills-zh. It costs 52 tokens per session (2,260 once invoked), scanned A, original, MIT.

A Chinese-language guide for using the browser-use command-line tool to control a web browser, including opening pages, clicking, entering text, taking screenshots, and extracting data.

In plain words
What is it for?
Use it for browser navigation, form filling, screenshots, web testing, and data collection. It also covers browser profiles and connecting to an existing Chrome session.
Why use it?
It provides a repeatable way to test websites and complete browser tasks instead of doing each action manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for browser navigation, form filling, screenshots, web testing, and data collection. It also covers browser profiles and connecting to an existing Chrome session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add L-LesterYu/OpenClaw-hot-skills-zh --skill browser-use-zh
Clone the repo
git clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zh

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for browser-use-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh/github.svg)](https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh)
Your own site
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for browser-use-zh

Your own site · 80×15
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/browser-use-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02260
Opus 5 $0.00026 $0.01130
Sonnet 5 $0.00010 $0.00452
Haiku 4.5 $0.00005 $0.00226

Measured 12d ago against content hash c0edd822d63c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

browser-use-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/browser-use-zh/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

使用 browser-use CLI 进行浏览器自动化

browser-use 命令提供快速、持久的浏览器自动化功能。后台守护进程在命令之间保持浏览器打开,每次调用的延迟约为 50ms。

前置条件

browser-use doctor    # 验证安装

安装详情请参见 https://github.com/browser-use/browser-use/blob/main/browser_use/skill_cli/README.md

核心工作流程

  1. 导航: browser-use open <url> — 如需要则启动浏览器
  2. 检查: browser-use state — 返回可点击元素及其索引
  3. 交互: 使用 state 返回的索引(browser-use click 5browser-use input 3 "text"
  4. 验证: browser-use statebrowser-use screenshot 确认结果
  5. 重复: 浏览器在命令之间保持打开
  6. 清理: 完成后使用 browser-use close

浏览器模式

browser-use open <url>                         # 默认:无头 Chromium
browser-use --headed open <url>                # 可见窗口
browser-use --profile "Default" open <url>      # 使用真实 Chrome 的 Default 配置文件(已有登录/Cookie)
browser-use --profile "Profile 1" open <url>   # 使用指定名称的 Chrome 配置文件
browser-use --connect open <url>               # 通过 CDP 自动发现运行中的 Chrome
browser-use --cdp-url ws://localhost:9222/... open <url>  # 通过 CDP URL 连接

--connect--cdp-url--profile 互斥。

命令

# 导航
browser-use open <url>                    # 导航到 URL
browser-use back                          # 后退
browser-use scroll down                   # 向下滚动(--amount N 指定像素数)
browser-use scroll up                     # 向上滚动
browser-use switch <tab>                  # 按索引切换标签页
browser-use close-tab [tab]              # 关闭标签页(不指定则关闭当前标签页)

# 页面状态 — 始终先运行 state 获取元素索引
browser-use state                         # URL、标题、可点击元素及索引
browser-use screenshot [path.png]         # 截图(不指定路径返回 base64,--full 截取整页)

# 交互 — 使用 state 返回的索引
browser-use click <index>                 # 按索引点击元素
browser-use click <x> <y>                 # 按像素坐标点击
browser-use type "text"                   # 在聚焦元素中输入文本
browser-use input <index> "text"          # 点击元素后输入文本
browser-use keys "Enter"                  # 发送键盘按键(也支持 "Control+a" 等)
browser-use select <index> "option"       # 选择下拉菜单选项
browser-use upload <index> <path>         # 上传文件到文件输入框
browser-use hover <index>                 # 悬停在元素上
browser-use dblclick <index>              # 双击元素
browser-use rightclick <index>            # 右键点击元素

# 数据提取
browser-use eval "js code"                # 执行 JavaScript,返回结果
browser-use get title                     # 页面标题
browser-use get html [--selector "h1"]    # 页面 HTML(或限定到选择器范围)
browser-use get text <index>              # 元素文本内容
browser-use get value <index>             # 输入框/文本域的值
browser-use get attributes <index>        # 元素属性
browser-use get bbox <index>              # 边界框(x, y, width, height)

# 等待
browser-use wait selector "css"           # 等待元素(--state visible|hidden|attached|detached,--timeout 毫秒)
browser-use wait text "text"              # 等待文本出现

# Cookie 管理
browser-use cookies get [--url <url>]     # 获取 Cookie(可按 URL 过滤)
browser-use cookies set <name> <value>    # 设置 Cookie(--domain, --secure, --http-only, --same-site, --expires)
browser-use cookies clear [--url <url>]   # 清除 Cookie
browser-use cookies export <file>         # 导出为 JSON
browser-use cookies import <file>         # 从 JSON 导入

# Python — 持久会话,可访问浏览器
browser-use python "code"                 # 执行 Python(变量在调用之间持久保存)
browser-use python --file script.py       # 运行文件
browser-use python --vars                 # 显示已定义的变量
browser-use python --reset                # 清除命名空间

# 会话管理
browser-use close                         # 关闭浏览器并停止守护进程
browser-use sessions                      # 列出活跃会话
browser-use close --all                   # 关闭所有会话

Read the full file on GitHub · 203 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 203 lines · 52 tokens per session scan A c0edd822d63c

Subscribe to this mod's changes

browser-use-zh is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 2,260 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens