A specialized tool for extracting rendered Markdown from JavaScript-heavy webpages and performing asynchronous site-wide crawls via Cloudflare APIs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install cloudflare-browser-rendering-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install cloudflare-browser-rendering-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Cloudflare Browser Rendering?
The Cloudflare Browser Rendering skill provides a robust bridge between basic static HTML fetching and full-scale manual browser automation. It utilizes Cloudflare REST APIs to render pages that rely heavily on JavaScript, ensuring that AI agents receive complete and accurate content rather than empty templates. This capability is essential for modern web environments where content is often injected dynamically after the initial page load.
By integrating this tool into your Openclaw Skills collection, you can efficiently convert complex web pages into clean Markdown. This is particularly valuable for building high-quality RAG pipelines, conducting technical research, or archiving documentation sites where site-wide crawling is required without the overhead of managing local browser instances.
Cloudflare Browser Rendering Use Cases
- Extracting content from Single Page Applications (SPAs) that require JavaScript execution.
- Crawling entire technical documentation sites or blogs for knowledge base preparation.
- Automating the gathering of data from sites that use modern web frameworks like React, Vue, or Next.js.
- Retrieving web content that requires specific user agents, cookies, or basic authentication.
- Preparing clean Markdown datasets for LLM summarization and analysis.
How Cloudflare Browser Rendering Works
- The skill identifies the target URL and determines if a single-page extraction or a multi-page crawl is required.
- For single pages, it calls the Cloudflare /markdown endpoint, applying rendering options like wait-until conditions to ensure the JS has fully executed.
- For site-wide tasks, it initiates an asynchronous crawl job with defined depth and page limits.
- The Cloudflare API processes the request in a serverless browser environment, bypassing the limitations of standard static scrapers.
- The tool polls for crawl completion and retrieves the results in structured JSON or Markdown format.
- Extracted data is then passed back to the agent or saved to local files for further processing.
Cloudflare Browser Rendering Setup
To use this skill, ensure Python 3 is installed and configure your Cloudflare credentials as environment variables:
export CLOUDFLARE_API_TOKEN="your_api_token"
export CLOUDFLARE_ACCOUNT_ID="your_account_id"
Install any required dependencies and run a test extraction:
python3 scripts/cf_markdown.py --url https://example.com --wait-until networkidle0
Cloudflare Browser Rendering Data Schema & Taxonomy
The skill produces structured data to ensure compatibility with various downstream AI workflows. The organization follows this taxonomy:
| Output Type | Format | Description |
|---|---|---|
| Page Content | Markdown | The final rendered version of a webpage, stripped of non-essential HTML tags. |
| Crawl Job | JSON | Metadata including job ID, status, and browser time consumption. |
| Crawl Results | JSON/MD | A collection of results from multiple pages, including source links and status codes. |
| Configuration | JSON | Support for custom cookies, headers, and authentication objects for complex sessions. |
Cloudflare Browser Rendering Advanced Features
- Advanced wait conditions such as networkidle0 and networkidle2 to handle complex loading sequences.
- Request filtering using regex patterns to exclude heavy assets like CSS or images, speeding up extraction.
- Full support for custom User-Agent strings and cookie injection to bypass basic bot detection.
- Asynchronous crawl management with the ability to start, wait for, and fetch results for large-scale data gathering.
- Flexible output options including direct JSON dumps for debugging or Markdown for direct LLM consumption.
SKILL.md
Loading
Related Openclaw Skills
X Growth Automation
A modular and reusable framework for building autonomous X/Twitter growth systems with built-in safety guardrails and multi-source content integration.
YouTube Playlist Image
A powerful automation tool for managing YouTube playlist thumbnails via the yutu CLI within the Openclaw Skills ecosystem.
Booking Hotel Search
A powerful hotel discovery skill that integrates real-time Booking.com data into your AI agent for instant availability and price comparisons.
Pilates (Session Planner, Form Coach, Progress Tracker)
A comprehensive AI-driven assistant for planning Pilates sessions, refining alignment, and tracking long-term core progression.
OpenClaw Daily News
An automated news aggregation and analysis tool designed to monitor the OpenClaw open-source AI agent ecosystem.
Giggle Video Generation
A powerful AI video generation skill supporting text and image-to-video workflows across multiple state-of-the-art models like Sora 2, Grok, and Kling.
Featured*
