跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 browser

Browser

通过CLI命令使用自然语言自动实现网页浏览器交互. 用户要求浏览网站,浏览网页,从网站取取出数据,取取截图,填表,点击按钮,或与网络应用程序互动时使用. 支持有浏览器库身份的远程浏览器会话,验证浏览器,自动CAPTCHA解析,以及住宅代理——理想的被保护网站和JavaScript-havy页面.

6044 安装量

官方网址:作者主页

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

通过 CLI 命令使用自然语言自动实现网页浏览器交互

何时用

用户要求浏览网站,浏览网页,从网站取取出数据,取取截图,填充表格,点击按钮,或与网络应用程序互动. 支持远程浏览器基础会话,包括浏览器基础身份、验证浏览器、自动CAPTCHA解析和resi

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Browser Automation、Setup check、Environment Selection (Local vs Remote)、Local mode、Remote mode (Browserbase)、When to choose which。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

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 Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.

Browser AutomationSetup checkEnvironment Selection (Local vs Remote)Local modeRemote mode (Browserbase)When to choose whichCommandsNavigationPage state (prefer snapshot over screenshot)InteractionCDP event tailingSession management

兼容:Requires the browse CLI (`npm install -g browse`). Remote Browserbase sessions need `BROWSERBASE_API_KEY`. Local mode uses Chrome/Chromium on your machine. · 许可:MIT · allowed-tools:Bash

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
browser
description
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 Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.
compatibility
Requires the browse CLI (`npm install -g browse`). Remote Browserbase sessions need `BROWSERBASE_API_KEY`. Local mode uses Chrome/Chromium on your machine.
allowed-tools
Bash实验字段,支持情况取决于客户端;字段声明本身不会授予工具权限。
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「browser」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-01dd6cbde2fb7fa3-%E6%B5%8F%E8%A7%88%E5%99%A8.html
请存为 .cursor/skills/browser/SKILL.md 或 .claude/skills/browser/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/browserbase/skills' --list

npx skills add 'https://github.com/browserbase/skills' --skill 'browser'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: browser description: 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 Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages. compatibility: "Requires the browse CLI (`npm install -g browse`). Remote Browserbase sessions need `BROWSERBASE_API_KEY`. Local mode uses Chrome/Chromium on your machine." license: MIT allowed-tools: Bash metadata: openclaw: requires: bins: - browse install: - kind: node package: "browse" bins: [browse] homepage: https://github.com/browserbase/skills --- # Browser Automation Automate browser interactions using the browse CLI with Claude. ## Setup check Before running any browser commands, verify the CLI is available: ```bash which browse || npm install -g browse ``` ## Environment Selection (Local vs Remote) The CLI supports explicit per-command environment flags. If you do nothing, the next session defaults to Browserbase when `BROWSERBASE_API_KEY` is set and to local otherwise. ### Local mode - `browse open --local` starts a clean isolated local browser - `browse open --auto-connect` attaches to an already-running debuggable Chrome; use `--local` when no debuggable Chrome is available - `browse open --cdp ` attaches to a specific CDP target - Best for: development, localhost, trusted sites, and reproducible runs ### Remote mode (Browserbase) - `browse open --remote` starts a Browserbase session - Without a local flag, Browserbase is also the default when `BROWSERBASE_API_KEY` is set - Provides: Browserbase Identity, Verified browsers, automatic CAPTCHA solving, residential proxies, session persistence - **Use remote mode when:** the target site has bot detection, CAPTCHAs, IP rate limiting, Cloudflare protection, or requires geo-specific access - Get credentials at https://browserbase.com/settings ### When to choose which - **Repeatable local testing / clean state**: `browse open --local` - **Reuse your local login/cookies**: `browse open --auto-connect` - **Simple browsing** (docs, wikis, public APIs): local mode is fine - **Protected sites** (login walls, CAPTCHAs, anti-scraping): use remote mode - **If local mode fails** with bot detection or access denied: switch to remote mode ## Commands Most driver commands work across local, remote, and CDP sessions after the daemon starts. ### Navigation ```bash browse open # Go to URL browse open --local # Go to URL in a clean local browser browse open --remote # Go to URL in a Browserbase session browse reload # Reload current page browse back # Go back in history browse forward # Go forward in history ``` ### Page state (prefer snapshot over screenshot) ```bash browse snapshot # Get accessibility tree with element refs (fast, structured) browse screenshot --path # Take visual screenshot (slow, uses vision tokens) browse get url # Get current URL browse get title # Get page title browse get text # Get text content (use "body" for all text) browse get html # Get HTML content of element browse get markdown [selector] # Get page content as markdown (defaults to body) browse get value # Get form field value ``` Use `browse snapshot` as your default for understanding page state — it returns the accessibility tree with element refs you can use to interact. Only use `browse screenshot` when you need visual context (layout, images, debugging). ### Interaction ```bash browse click # Click element by ref from snapshot (e.g., @0-5) browse type # Type text into focused element browse fill # Fill input; add --press-enter if Enter is needed browse select # Select dropdown option(s) browse upload # Upload file(s) to browse press # Press key (Enter, Tab, Escape, Cmd+A, etc.) browse mouse drag # Drag from one point to another browse mouse scroll # Scroll at coordinates browse highlight # Highlight element on page browse is visible # Check if element is visible browse is checked # Check if element is checked browse wait [arg] # Wait for: load, selector, timeout ``` ### CDP event tailing ```bash browse cdp # Stream CDP events as NDJSON from any target browse cdp 9222 # Attach to local Chrome on port 9222 browse cdp ws://localhost:9222/devtools/browser/... # Full WebSocket URL browse cdp --domain Network # Only Network events browse cdp --domain Network --domain Console # Multiple domains browse cdp --pretty # Human-readable output browse cdp > events.jsonl # Pipe to file browse cdp | jq '.method' # Filter with jq ``` The `cdp` command connects directly to any Chrome DevTools Protocol target and streams events. It does **not** use the daemon — it's a standalone, long-running process. Press Ctrl+C to stop. Default domains: Network, Console, Runtime, Log, Page. ### Session management ```bash browse stop # Stop the browser daemon browse status # Check daemon status and resolved mode browse tab list # List all open tabs browse tab switch # Switch to tab by index or target ID browse tab close [index-or-target-id] # Close tab ``` ### Typical workflow If the environment matters, put `--local`, `--remote`, `--auto-connect`, or `--cdp ` on the first browser command. 1. `browse open --local` or `browse open --remote` — navigate to the page 2. `browse snapshot` — read the accessibility tree to understand page structure and get element refs 3. `browse click ` / `browse type ` / `browse fill ` — interact using refs from snapshot 4. `browse snapshot` — confirm the action worked 5. Repeat 3-4 as needed 6. `browse stop` — close the browser when done ## Quick Example ```bash browse open https://example.com browse snapshot # see page structure + element refs browse click @0-5 # click element with ref 0-5 browse get title browse stop ``` ## Mode Comparison | Feature | Local | Browserbase | |---------|-------|-------------| | Speed | Faster | Slightly slower | | Setup | Chrome required | API key required | | Reuse existing local cookies | With `browse open --auto-connect` | N/A | | Verified browser | No | Yes (Browserbase Verified browser via Identity) | | CAPTCHA solving | No | Yes (automatic reCAPTCHA/hCaptcha) | | Residential proxies | No | Yes (201 countries, geo-targeting) | | Session persistence | No | Yes (cookies/auth persist via contexts) | | Best for | Development/simple pages | Protected sites, Browserbase Identity + Verified access, production scraping | ## Best Practices 1. **Choose the local strategy deliberately**: use `browse open --local` for clean state, `browse open --auto-connect` for existing local credentials, and `browse open --remote` for protected sites 2. **Always `browse open` first** before interacting 3. **Use `browse snapshot`** to check page state — it's fast and gives you element refs 4. **Only screenshot when visual context is needed** (layout checks, images, debugging) 5. **Use refs from snapshot** to click/interact — e.g., `browse click @0-5` 6. **`browse stop`** when done to clean up the browser session and clear the env override ## Troubleshooting - **"No active page"**: Run `browse stop`, then check `browse status`. If it still says running, kill the zombie daemon with `pkill -f "browse.*daemon"`, then retry `browse open` - **Chrome not found**: Install Chrome, use `browse open --auto-connect` if you already have a debuggable Chrome running, or switch to `browse open --remote` - **Action fails**: Run `browse snapshot` to see available elements and their refs - **Browserbase fails**: Verify API key is set ## Switching to Remote Mode Switch to remote when you detect: CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot detection pages ("Checking your browser..."), HTTP 403/429, empty pages on sites that should have content, or the user asks for it. Don't switch for simple sites (docs, wikis, public APIs, localhost). ```bash browse open --local # clean isolated local browser browse open --auto-connect # attach to existing debuggable Chrome browse open --remote # Browserbase session ``` Mode flags are applied when a session starts. After `browse stop`, the next start falls back to env-var-based auto detection. Use `browse status` to inspect the resolved mode and target while the daemon is running. For detailed examples, see [EXAMPLES.md](EXAMPLES.md). For API reference, see [REFERENCE.md](REFERENCE.md).

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…