Markdown Extract for Openclaw

A high-performance utility designed to convert web pages into clean, developer-friendly markdown via the markdown.new API.

aviclaw
v1.0.0
Feb 15, 2026
0
1.2k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install markdown-extract

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 markdown-extract 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 Markdown Extract?

Markdown Extract is a specialized tool within the Openclaw Skills ecosystem that streamlines the process of fetching and cleaning web content. By integrating with the markdown.new API, it removes the clutter of ads, tracking scripts, and navigation elements, leaving only the core content in a structured markdown format. This makes it an invaluable asset for developers who need to feed high-quality data into Large Language Models (LLMs) or maintain technical documentation.

The skill provides flexibility by offering different extraction strategies depending on the source material. Whether you are dealing with a simple blog post or a complex single-page application (SPA), Markdown Extract ensures the resulting text is accurate and readable, enhancing the utility of your Openclaw Skills setup.

Markdown Extract Use Cases

  • Extracting clean text from technical documentation for AI-assisted coding and debugging.
  • Converting blog posts or news articles into markdown for personal knowledge management systems.
  • Gathering context from JavaScript-heavy websites for research and analysis.
  • Pre-processing web data for training or fine-tuning local AI models.

How Markdown Extract Works

  1. The user initiates a request by providing a URL and selecting an extraction method through the Openclaw Skills interface.
  2. The skill communicates with the markdown.new API using either a GET or POST request.
  3. The backend identifies the best way to parse the page, whether through simple content negotiation or full browser rendering.
  4. The resulting markdown is returned to the user, handled by the agent for further processing.

Markdown Extract Setup

To start using this skill within your environment, ensure you have access to the Openclaw Skills framework and run the following command to verify connectivity:

!markdown-extract https://example.com

No additional API keys are required as it leverages the public markdown.new endpoint by default.

Markdown Extract Data Schema & Taxonomy

The skill processes inputs and generates outputs based on the following structure:

Parameter Type Description
url String The target web address to extract content from.
method String Options: auto (default), ai (LLM-based), or browser (full JS rendering).
output String The processed markdown content or error details.

Internal logic handles content negotiation using the Accept: text/markdown header for the fastest possible results.

Markdown Extract Advanced Features

  • Multi-method support allowing users to toggle between speed (auto) and accuracy (browser).
  • Intelligent Cloudflare block detection with built-in fallback mechanisms for higher success rates.
  • AI-powered conversion using Cloudflare Workers AI for superior formatting of complex layouts.
  • Headless browser rendering for full compatibility with modern, JavaScript-dependent web applications.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*