做什么
通过 Chrome DevTools 协议实现交互式浏览器自动化
技能库 智客分类:Agent 工作流 browser-tools
交互式浏览器自动化通过Chrome DevTools协议. 需要与网页交互时使用,测试前端,或者需要用户与可见浏览器交互时使用.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
通过 Chrome DevTools 协议实现交互式浏览器自动化
- 在真正的浏览器中测试前端代码
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 Tools、Setup、Start Chrome、Navigate、Evaluate JavaScript、Screenshot。
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。
Interactive browser automation via Chrome DevTools Protocol. Use when you need to interact with web pages, test frontends, or when user interaction with a visible browser is required.
Browser ToolsSetupStart ChromeNavigateEvaluate JavaScriptScreenshotPick ElementsCookiesExtract Page ContentWhen to UseEfficiency GuideDOM Inspection Over Screenshots
来源分类:skills.sh agent-skill
namebrowser-toolsdescription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 ↗
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。
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-tools」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-3fe225d384cda04e-%E6%B5%8F%E8%A7%88%E5%99%A8%E5%B7%A5%E5%85%B7.html 请存为 .cursor/skills/browser-tools/SKILL.md 或 .claude/skills/browser-tools/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
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/badlogic/pi-skills' --list
npx skills add 'https://github.com/badlogic/pi-skills' --skill 'browser-tools'
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。
Chrome DevTools Protocol tools for agent-assisted web automation. These tools connect to Chrome running on :9222 with remote debugging enabled.
Run once before first use:
cd {baseDir}/browser-tools
npm install
{baseDir}/browser-start.js # Fresh profile
{baseDir}/browser-start.js --profile # Copy user's profile (cookies, logins)
Launch Chrome with remote debugging on :9222. Use --profile to preserve user's authentication state.
{baseDir}/browser-nav.js https://example.com
{baseDir}/browser-nav.js https://example.com --new
Navigate to URLs. Use --new flag to open in a new tab instead of reusing current tab.
{baseDir}/browser-eval.js 'document.title'
{baseDir}/browser-eval.js 'document.querySelectorAll("a").length'
Execute JavaScript in the active tab. Code runs in async context. Use this to extract data, inspect page state, or perform DOM operations programmatically.
{baseDir}/browser-screenshot.js
Capture current viewport and return temporary file path. Use this to visually inspect page state or verify UI changes.
{baseDir}/browser-pick.js "Click the submit button"
IMPORTANT: Use this tool when the user wants to select specific DOM elements on the page. This launches an interactive picker that lets the user click elements to select them. The user can select multiple elements (Cmd/Ctrl+Click) and press Enter when done. The tool returns CSS selectors for the selected elements.
Common use cases:
{baseDir}/browser-cookies.js
Display all cookies for the current tab including domain, path, httpOnly, and secure flags. Use this to debug authentication issues or inspect session state.
{baseDir}/browser-content.js https://example.com
Navigate to a URL and extract readable content as markdown. Uses Mozilla Readability for article extraction and Turndown for HTML-to-markdown conversion. Works on pages with JavaScript content (waits for page to load).
Don't take screenshots to see page state. Do parse the DOM directly:
// Get page structure
document.body.innerHTML.slice(0, 5000)
// Find interactive elements
Array.from(document.querySelectorAll('button, input, [role="button"]')).map(e => ({
id: e.id,
text: e.textContent.trim(),
class: e.className
}))
Wrap everything in an IIFE to run multi-statement code:
(function() {
// Multiple operations
const data = document.querySelector('#target').textContent;
const buttons = document.querySelectorAll('button');
// Interactions
buttons[0].click();
// Return results
return JSON.stringify({ data, buttonCount: buttons.length });
})()
Don't make separate calls for each click. Do batch them:
(function() {
const actions = ["btn1", "btn2", "btn3"];
actions.forEach(id => document.getElementById(id).click());
return "Done";
})()
(function() {
const text = "HELLO";
for (const char of text) {
document.getElementById("key-" + char).click();
}
document.getElementById("submit").click();
return "Submitted: " + text;
})()
Extract structured state in one call:
(function() {
const state = {
score: document.querySelector('.score')?.textContent,
status: document.querySelector('.status')?.className,
items: Array.from(document.querySelectorAll('.item')).map(el => ({
text: el.textContent,
active: el.classList.contains('active')
}))
};
return JSON.stringify(state, null, 2);
})()
If DOM updates after actions, add a small delay with bash:
sleep 0.5 && {baseDir}/browser-eval.js '...'
Always start by understanding the page structure:
(function() {
return {
title: document.title,
forms: document.forms.length,
buttons: document.querySelectorAll('button').length,
inputs: document.querySelectorAll('input').length,
mainContent: document.body.innerHTML.slice(0, 3000)
};
})()
Then target specific elements based on what you find.
Agent 工作流
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
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
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
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…