personal-agent-browser一个为你的个人数字大脑设计的浏览器自动化技能。它调用你本地安装的 agent-browser CLI，安全地访问网页，提取标题和内容，并返回结构化摘要，让 AI 助手能理解并总结网页信息。 **使用场景**： (1) 用户要求：“帮我查看一下我的技能在 ClawHub 上的页面” (2) 用户希望 AI 自动抓取...
Install via ClawdBot CLI:
clawdbot install awublack/personal-agent-browserGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://clawhub.ai/awublack/awublack-personal-memory-systemAI Analysis
The skill executes local CLI commands via child_process.exec, which poses a medium execution risk if the agent-browser tool is compromised, but it does not exfiltrate data to external servers. The external URL example is user-provided input, not a hardcoded call, and the skill's design emphasizes local-only processing with transparent, auditable code.
Audited Apr 17, 2026 · audit v1.0
Generated May 11, 2026
Users ask the AI to fetch and summarize content from specific web pages for research or learning. The skill extracts structured data from the URL, enabling quick understanding without manual browsing.
Users set up automated checks of competitor websites or news pages. The skill periodically retrieves page titles and content, allowing the AI to detect changes and summarize updates.
Users ask the AI to capture a web article and store its summary in their personal memory system. The skill provides clean structured output that can be integrated with local knowledge databases.
Users need to access or scrape pages containing sensitive data (e.g., personal dashboards, private repositories) without sending information to third-party services. The skill operates entirely locally.
Developers ask the AI to fetch the latest documentation or changelog from a specific URL. The skill returns titles and markdown content, which the AI can summarize or compare with previous versions.
Offer the basic skill for free as part of a personal AI assistant package, with premium features like screenshot capture or form interaction available via subscription.
License the skill to companies that require local-only browser automation for compliance reasons, selling it as part of a suite of local AI skills.
Charge third-party AI platform developers a fee to integrate this skill into their systems as a certified local extension, ensuring their users get trusted browser access.
💬 Integration Tip
To integrate, simply place the skill folder in OpenClaw's 'skills' directory and ensure the agent-browser CLI is installed globally via npm.
Scored Jul 11, 2026
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
通过已登录的Edge或Chrome浏览器，利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。
Send and receive SMS/RCS via Google Messages web interface (messages.google.com). Use when asked to "send a text", "check texts", "SMS", "text message", "Google Messages", or forward incoming texts to other channels.
High-performance browser automation for heavy scraping, multi-tab management, and precise DOM extraction. Use this when you need speed, reliability, or advanced state management (cookies/local storage) beyond standard web fetching.