Browser Agent

通过 index.js 以命令行标志驱动 Playwright：打开目标 URL、截图、读取标题、按选择器提取文本、点击元素、填写输入框，并保存或加载 cookies/storage state；截图与提取结果写入 out/ 目录。需要 Node 运行环境与 Playwright。

热度 55.19

最近更新 2026-05-11 17:34:16

分类：自动化依赖：联网浏览搜索 / 代码执行 / 读写文件应用场景：工作流 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add neo1307-browser-agent

Metadata

name: browser-agent
description: Browser automation with Playwright for opening pages, taking screenshots, finding or clicking DOM elements, filling forms, extracting text, and managing cookies/session state. Use when Codex needs deterministic browser control against real web pages, smoke-testing a site, grabbing DOM evidence, or automating straightforward UI flows.

Use Playwright-backed browser control for reproducible page actions.

Run index.js with a target URL.
Use action flags to open, screenshot, extract title/text, click selectors, fill inputs, or save/load session state.
Keep selectors explicit when clicking or filling.
Save evidence (screenshots / extracted text) to out/.

node skills/browser-agent/index.js --url https://example.com --screenshot out/example.png --title --extract h1