playwright-controllerBrowse webpages using Playwright with automatic loading wait, screenshots, and text extraction. Use playwright:fetch or playwright:screenshot commands. API:...
Install via ClawdBot CLI:
clawdbot install mrchenkuan/playwright-controllerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://baike.baidu.com/item/兴盛优选/23451097AI Analysis
The skill's external URL usage (baike.baidu.com) appears to be example URLs for demonstration purposes consistent with the skill's stated web browsing functionality. The eval() reference is concerning but appears in documentation rather than active code, and the skill operates locally with file output rather than data exfiltration.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Marketing teams can use this skill to capture screenshots and extract text from competitor websites, monitoring product updates, pricing changes, and promotional content. The mobile simulation ensures accurate representation of how content appears on smartphones, which is crucial for analyzing mobile-first strategies.
Legal or compliance departments can automate the process of capturing webpage evidence for audits or record-keeping. The skill's ability to wait for full page load and extract clean text ensures reliable documentation of online statements, terms of service, or public announcements.
Development teams can utilize the element-specific screenshot feature to verify UI components render correctly across different pages. The automatic waiting and full resource loading mimic real user experience, helping identify rendering issues before deployment.
Research analysts can systematically gather visual and textual data from e-commerce sites, news portals, or social media for trend analysis. The text extraction facilitates NLP processing, while screenshots preserve layout context for qualitative review.
SEO specialists can track how their pages or competitors' pages appear in mobile search results, checking meta descriptions, headings, and content structure. The tool's consistent mobile emulation provides standardized data points for performance comparison over time.
Integrate this skill into a subscription-based platform offering automated website auditing, competitor tracking, and compliance reporting services. Agencies can charge clients monthly for regular monitoring reports that combine screenshots with extracted insights.
Package the crawling and extraction capabilities as an API service, selling structured webpage data (text and images) to enterprises needing large-scale web monitoring. Offer tiered pricing based on request volume and data retention needs.
License the technology to financial institutions or legal firms needing automated evidence collection for regulatory requirements. Provide a customizable dashboard where clients can schedule captures, manage archives, and generate audit-ready reports.
💬 Integration Tip
Start by using the CLI commands for quick testing, then integrate the JavaScript APIs into existing Node.js applications for automation workflows.
Scored Jun 17, 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.