WebFetch MD for Openclaw

A high-performance utility to scrape any webpage and transform it into clean, well-formatted Markdown while preserving all image links.

shijianwen
v1.1.0
Feb 15, 2026
0
2.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install webfetch-md

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install webfetch-md 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 WebFetch MD?

WebFetch MD is a specialized tool designed for the Openclaw Skills framework that streamlines the process of extracting meaningful content from the web. It intelligently identifies the main body of a webpage, stripping away distracting elements like advertisements, sidebars, and navigation menus to deliver a pure Markdown output.

By leveraging industry-standard libraries like Turndown and Cheerio, it ensures high-fidelity conversion that is perfect for AI ingestion or personal knowledge management. Whether you are building an automated research pipeline or simply archiving articles, this skill provides a robust bridge between HTML and Markdown, making it a vital addition to the Openclaw Skills library.

WebFetch MD Use Cases

  • Scraping articles for AI model training or RAG (Retrieval-Augmented Generation) pipelines.
  • Archiving blog posts and news articles into personal notes or PKM systems.
  • Automating web research and data collection within Openclaw Skills workflows.
  • Converting online documentation pages into offline-readable Markdown files for developers.

How WebFetch MD Works

  1. The tool initiates a fetch request to the target URL, simulating a real browser via User-Agent headers to ensure access.
  2. It parses the raw HTML using Cheerio to build a searchable DOM structure for analysis.
  3. A smart extraction algorithm prioritizes content containers like
    ,
    , or specific CSS classes (e.g., .post-content) to find the core text.
  4. It converts relative image and link paths into absolute URLs to maintain data integrity across different environments.
  5. The Turndown library converts the cleaned HTML into standard Markdown format while preserving formatting like headers and lists.
  6. It returns a structured JSON response containing the Markdown content, page title, and image metadata for use in other Openclaw Skills.

WebFetch MD Setup

To get started with this skill in your environment, ensure you have Node.js installed. You can run it directly via npx or integrate it into your Openclaw Skills configuration.

# Basic usage via npx
npx webfetch-md --url https://example.com

# Save content directly to a file using jq
npx webfetch-md https://example.com | jq -r '.markdown' > article.md

WebFetch MD Data Schema & Taxonomy

The skill returns a unified JSON object to ensure compatibility across different Openclaw Skills integrations and CLI pipes.

Field Type Description
success Boolean Indicates if the fetch and conversion were successful
title String The extracted title of the webpage
markdown String The full content converted into clean Markdown
images Array A list of all absolute image URLs found in the content
imageCount Number Total number of images processed
contentLength Number The character count of the resulting Markdown

WebFetch MD Advanced Features

  • Intelligent content prioritization using a fallback ladder starting from semantic tags down to the document body.
  • Automatic filtering of non-essential elements including scripts, styles, headers, footers, and comment sections.
  • Direct integration as a module for custom JavaScript and Node.js applications.
  • Seamless CLI support with JSON output for easy automation within Openclaw Skills scripts.
  • Robust error handling with descriptive feedback to debug failed scrapers or restricted URLs.

SKILL.md


Loading

Related Openclaw Skills

Featured*