agent-browser-skill
Provides tools for browser automation, allowing AI agents to interact with web pages and capture UI state.
Install
mkdir -p .claude/skills/agent-browser-skill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3575" && unzip -o skill.zip -d .claude/skills/agent-browser-skill && rm skill.zipInstalls to .claude/skills/agent-browser-skill
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
基于 agent-browser CLI 的浏览器自动化工具。提供快照获取、元素交互、截图等功能。推荐用于需要页面快照分析、通过 ref 引用交互元素的场景。Key capabilities
- →Get core workflow and command guides for agent-browser
- →Get full command parameters and script templates for agent-browser
- →Obtain dedicated skill guides for specific web pages
- →Automate Electron desktop applications
- →Automate Slack workspace operations
- →Save screenshots using a system-injected environment variable
How it works
This skill provides access to the agent-browser CLI's documentation and specialized guides for browser automation tasks. It directs users to dynamically load current instructions for various scenarios.
Inputs & outputs
When to use agent-browser-skill
- →Capturing browser snapshots for debugging
- →Automating interaction with a web application
- →Extracting data from non-standard web interfaces
About this skill
Agent Browser 浏览器自动化
基于 Vercel Labs 官方开发的 agent-browser CLI 浏览器自动化工具，专为 AI Agent（智能体）设计。
⚠️ 启动指引：动态获取最新指南
为了确保你获取的命令和工作流与当前系统安装的 agent-browser 版本（当前为 v0.27.0）完全匹配且不落后，此文件仅作为引导存根（Stub），不作为主要的使用指南。
在执行任何浏览器自动化操作之前，你必须优先通过命令行动态加载最新的详细工作流和命令指南：
# 1. 运行此命令获取核心工作流、常用模式和疑难解答（最重要！）
agent-browser skills get core
# 2. 运行此命令获取包含完整命令参数、修饰符和脚本模板的完整参考指南
agent-browser skills get core --full
快速导航
如果你需要处理非标准 Web 页面（例如桌面应用或特定协同工具），请通过以下命令获取专用技能指南：
- 自动化 Electron 桌面应用 (如 VS Code, Slack, Notion)：
agent-browser skills get electron - 自动化 Slack 工作区操作：
agent-browser skills get slack - 探索性 QA 测试 / 找 Bug 场景：
agent-browser skills get dogfood
截图路径约定
必须优先使用系统注入的 SCREENSHOT_DIR 环境变量保存截图，不要手写 /tmp/screenshots 或 ./step1.png 这类路径：
: "${SCREENSHOT_DIR:?SCREENSHOT_DIR 未设置}"
agent-browser screenshot "${SCREENSHOT_DIR}/case_11_step1.png"
Prerequisites
Limitations
- →This file does not serve as the primary usage guide.
- →Users must dynamically load the latest detailed workflow and command guides.
- →Screenshot paths must use the SCREENSHOT_DIR environment variable.
How it compares
This skill provides dynamic, up-to-date guidance for a specific CLI tool, contrasting with static, potentially outdated documentation.
Compared to similar skills
agent-browser-skill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agent-browser-skill (this skill) | 4 | 2mo | Review | Intermediate |
| dev-browser | 53 | 4mo | Review | Intermediate |
| agent-browser | 30 | 3mo | Review | Intermediate |
| browser-tools | 6 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by MGdaasLab
View all by MGdaasLab →You might also like
dev-browser
SawyerHood
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
agent-browser
vercel-labs
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
browser-tools
Whamp
Lightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.
browser
cexll
This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.
browserwing-executor
browserwing
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
go-rod-master
rootcastleco
Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.