Dev Browser

AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。

Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Search ChatGPT and extract the full response + hydration JSON that powers the UI. Attaches to a running Chrome instance (port 9222 by default), opens ChatGPT, submits a query, waits for the streamed response, and returns structured data: messages, product cards, hydration JSON, and API calls. Use when asked to "search chatgpt", "ask chatgpt", "chatgpt search", "get chatgpt response", or "scrape chatgpt".

Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.

用于编写 Playwright 测试、修复不稳定测试、调试失败、实现页面对象模型 (Page Object Model)、配置 CI/CD、优化性能、模拟 API、处理身份验证或 OAuth、测试可访问性 (axe-core)、文件上传/下载、日期/时间模拟、WebSockets、地理定位、权限、多标签/弹出窗口流程、移动/响应式布局、触摸手势、GraphQL、错误处理、离线模式、多人协作、第三方服务（付款、电子邮件验证）、控制台错误监控、全局设置/拆卸、测试注解（skip, fixme, slow）、测试标签（@smoke, @fast, @critical, 使用 --grep 过滤）、项目依赖项、安全测试（XSS, CSRF, 身份验证）、性能预算（Web Vitals, Lighthouse）、iframe、组件测试、canvas/WebGL、服务工作线程/PWA、测试覆盖率、i18n/本地化、Electron 应用或浏览器扩展测试。涵盖 E2E、组件、API、视觉、可访问性、安全、Electron 和扩展测试。