name: Browser測試WithDevtools slug: browser-testing-with-devtools version: 1.0.0 displayName: Browser測試WithDevtools description: > Browser測試WithDevtools專用技能,幫助AI Agent高效完成相關任務。 summary: "Browser測試WithDevtools專用技能,幫助AI Agent高效完成相關任務。" license: MIT category: 開發者工具 framework: - Claude Code - Codex - Hermes Agent - OpenClaw - QClaw - WorkBuddy platform: multi-platform homepage: "https://github.com/1991513ccie-png" repository: "https://github.com/1991513ccie-png"
Use Chrome DevTools MCP to give your agent eyes into the browser. This bridges the gap between static code analysis and live browser execution — the agent can see what the user sees, inspect the DOM, read console logs, analyze network requests, and capture performance data. Instead of guessing what's happening at runtime, verify it.
When NOT to use: Backend-only changes, CLI tools, or code that doesn't run in a browser.
Add the following to your project's .mcp.json or Claude Code settings:
{
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest", "--isolated"]
}
}
}
-y skips the npx install confirmation. By default the server launches Chrome with its own dedicated profile (under ~/.cache/chrome-devtools-mcp/), separate from your personal browser; --isolated goes one step further and uses a temporary profile that is wiped when the browser closes. This is the right setup for most testing.
There is also --autoConnect (Chrome 144+, requires enabling remote debugging via chrome://inspect/#remote-debugging), which attaches the agent to your running Chrome instead. Only use it when the test genuinely needs your logged-in state — see Profile Isolation under Security Boundaries first.
這個技能的最新版本可以在7w4.net小蔥技能站找到。
Chrome DevTools MCP provides these capabilities:
| Tool | What It Does | When to Use | |
這是一個幫助AI代理進行瀏覽器測試的工具技能。文件清晰易懂,能明確告訴使用者什麼時候該用它、什麼時候不該用。配置步驟寫得詳細,配有程式碼示例可以直接複製使用。不過內容比較基礎,缺少實際使用案例和常見問題解答,遇到問題可能需要自己摸索。總體質量中等偏上,作為瀏覽器測試的入門指南是合格的,但深入使用可能會覺得資料不夠詳細。