browser-rendering
This skill enables agents to render and interact with JavaScript-heavy websites through Cloudflare's infrastructure, extracting structured data from pages that require browser execution. Built for the Agent Skills standard, it integrates seamlessly with Claude, OpenAI, and other compatible agent platforms to handle complex scraping workflows at scale.
browser-rendering is a skill that enables agents to automate web scraping and data extraction from dynamic JavaScript-rendered pages. It supports headless browser automation through tools like Puppeteer and Playwright, allowing you to extract structured data from websites that require browser execution. The skill integrates seamlessly with Claude, OpenAI, and other compatible agent platforms to handle complex scraping workflows at scale through Cloudflare's infrastructure.
AI-generated summary based on this skill's SKILL.md
Install
null-shot/cloudflare-skills/browser-rendering · repository language: TypeScript
git clone https://github.com/null-shot/cloudflare-skills
cp -r cloudflare-skills/browser-rendering ~/.claude/skills/browser-renderingFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is browser-rendering and how does it handle web scraping with puppeteer or playwright?
browser-rendering is a skill that enables agents to automate web scraping and data extraction from dynamic JavaScript-rendered pages. It supports headless browser automation through tools like Puppeteer and Playwright, allowing you to extract structured data from websites that require browser execution. The skill integrates seamlessly with Claude, OpenAI, and other compatible agent platforms to handle complex scraping workflows at scale through Cloudflare's infrastructure.
Can browser-rendering take screenshots and generate PDFs of web pages programmatically?
Yes, browser-rendering supports capturing screenshots and generating PDFs of web pages programmatically. This capability allows you to automate visual documentation of websites, convert HTML to PDF, and capture pages as images through a REST API interface. These features are built into the skill's core functionality for comprehensive web page rendering and conversion tasks.
How does browser-rendering integrate with Cloudflare Workers for edge-based processing?
browser-rendering enables headless browser automation to be integrated directly into Cloudflare Workers, allowing you to perform browser rendering and data extraction at the edge network. This integration lets you run automated browser testing and web scraping operations closer to your users, reducing latency and improving performance for large-scale automation workflows.
Does browser-rendering support natural language web selectors and AI-native automation?
browser-rendering includes support for building AI-native automation workflows using natural language selectors and MCP integration. This advanced capability allows agents to interact with web pages using more intuitive, language-based instructions rather than traditional CSS or XPath selectors, making automation workflows more accessible and flexible.
What browser automation capabilities does browser-rendering provide for testing purposes?
browser-rendering enables automated browser testing with assertions and debugging capabilities, allowing you to validate web application behavior programmatically. The skill supports comprehensive testing workflows that can be integrated into your CI/CD pipelines and agent automation systems for reliable quality assurance.
How does browser-rendering extract structured data from dynamic websites?
browser-rendering extracts structured data from dynamic websites by executing JavaScript and rendering pages fully before data extraction. This approach ensures that content loaded asynchronously or generated by client-side frameworks is captured completely, making it ideal for scraping JavaScript-rendered content and converting it into structured, usable data for your agents.
SKILL.md
rendered from the published skill — quoted content, verbatim
Browser Rendering
Cloudflare Browser Rendering provides headless Chrome instances on the global edge network for web scraping, screenshots, PDF generation, and automated testing. Choose from REST API for simple tasks or Workers Bindings (Puppeteer, Playwright, Stagehand) for advanced automation.
Choosing an Integration Method
| Method | Use Case | Complexity |
|---|---|---|
| REST API | Simple screenshots, PDFs, markdown extraction, structured data | Low - just HTTP requests |
| Puppeteer | Industry-standard Chrome automation, porting existing scripts | Medium - familiar API |
| Playwright | Modern cross-browser automation, AI agent integration (MCP) | Medium - developer-friendly |
| Stagehand | AI-native automation with natural language selectors | Low - resilient to site changes |
REST API
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 5 files
browser-rendering/SKILL.md
browser-rendering/references/limits.md
browser-rendering/references/patterns.md
browser-rendering/references/puppeteer.md
browser-rendering/references/testing.md