← 返回 Skills 市场

Browser

Name: Browser
Author: pshotts

作者 pshotts · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

14635

总下载

260

当前安装

版本数

在 OpenClaw 中安装

/install browser

功能描述

Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.

使用说明 (SKILL.md)

SKILL: Browser

This skill uses a headless browser (Puppeteer) to render web pages and extract clean, readable content.

Puppeteer Browser Automation

This is a custom skill generated by OpenClaw to handle headless web browsing. It utilizes the Puppeteer library to navigate to websites, interact with DOM elements, click buttons, and scrape data for the agent's context.

Usage

openclaw browser read \x3Curl> - Renders the page and returns its text content.

安全使用建议

This skill appears benign for rendering and reading web pages. Before installing, be aware that it opens arbitrary URLs with Puppeteer using disabled browser sandbox flags, so it is safest to run it in a container or otherwise isolated environment, especially for unknown websites.

功能分析

Type: OpenClaw Skill Name: browser Version: 1.0.0 The skill provides a standard headless browser utility using Puppeteer to extract text content from URLs. The code in index.js is straightforward and functional, and the documentation in SKILL.md and README.md accurately describes its purpose without any indicators of malicious intent, data exfiltration, or prompt injection.

能力评估

ℹ Purpose & Capability

The stated purpose is to render web pages and extract readable text, which matches the included Puppeteer code.

✓ Instruction Scope

The usage is scoped to a single command, `read <url>`, and the code only navigates to that URL and prints page text.

ℹ Install Mechanism

The README declares a Puppeteer dependency, but the provided artifacts include no install spec, package manifest, or lockfile to pin or verify it.

ℹ Credentials

Launching a headless browser is purpose-aligned, but the code disables Chromium sandboxing while rendering arbitrary URLs.

✓ Persistence & Privilege

No credentials, persistent storage, background worker, or privileged account access are shown; the browser is closed after each run.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install browser
安装完成后，直接呼叫该 Skill 的名称或使用 /browser 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the Browser skill. - Uses Puppeteer to render web pages and extract clean, readable content. - Supports headless web browsing, DOM interaction, and data scraping. - Provides a command to read and return text from a specified URL.

元数据

Slug browser

版本 1.0.0

许可证 —

累计安装 273

当前安装数 260

历史版本数 1

常见问题

Browser 是什么？

Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 14635 次。

如何安装 Browser？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install browser」即可一键安装，无需额外配置。

Browser 是免费的吗？

是的，Browser 完全免费（开源免费），可自由下载、安装和使用。

Browser 支持哪些平台？

Browser 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Browser？

由 pshotts（@pshotts）开发并维护，当前版本 v1.0.0。