An intelligent tool that converts complex web content into clean, readable Markdown using a prioritized list of high-performance fetching services.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install markdown-fetcher
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 markdown-fetcher 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 Fetcher?
Markdown Fetcher is a specialized utility designed to transform unstructured web URLs into structured, clean Markdown text. By leveraging a hierarchy of powerful conversion services, it ensures that developers can easily ingest web data for AI processing, documentation, or personal knowledge management. As a key component of Openclaw Skills, it solves the problem of messy HTML scraping by providing a refined text output ready for LLM analysis.
The skill is built with resilience in mind, featuring a multi-stage fallback system that attempts various high-quality converters before resorting to local scraping methods. This makes it an essential tool for any workflow that requires automated content extraction or web-to-text transformation.
Markdown Fetcher Use Cases
- Scraping web articles and blog posts for deep reading or content analysis.
- Converting online documentation into Markdown format for training AI models or archival.
- Extracting raw data from web pages to be used in automated Openclaw Skills workflows.
- Organizing web-based research into simplified, searchable text files.
How Markdown Fetcher Works
- The skill receives a target URL from the user or another agent.
- It attempts to fetch the content using the primary service, markdown.new, which is optimized for modern web architectures including those behind Cloudflare.
- If the primary service fails, it moves to the first backup service, defuddle.md.
- If still unsuccessful, it utilizes r.jina.ai, a highly stable and universal web-to-markdown fetching service.
- As a final resort, it executes a localized scraping process using the Scrapling tool to ensure the content is captured regardless of remote service availability within Openclaw Skills.
Markdown Fetcher Setup
To use the web-based conversion services, no additional installation is required. To enable the local fallback capability, install the Scrapling CLI tool using the following command:
pip install scrapling
You can then test the local extraction manually:
scrapling -u "https://example.com"
Markdown Fetcher Data Schema & Taxonomy
Markdown Fetcher organizes its operations through a prioritized service schema to ensure data integrity and format consistency:
| Priority | Method | Recommended Use Case |
|---|---|---|
| 1. Primary | markdown.new | Cloudflare-hosted sites and modern web apps |
| 2. Backup | defuddle.md | General web content conversion |
| 3. Stable | r.jina.ai | Universal fetching and robust content extraction |
| 4. Local | Scrapling | Fallback for restricted or private web pages |
The resulting output is a standardized Markdown string containing the main body text, headers, and links of the source page.
Markdown Fetcher Advanced Features
- Intelligent tiered fallback logic that guarantees high success rates across diverse website architectures.
- Optimized handling of Cloudflare-protected sites through specialized conversion endpoints.
- Integration with local CLI tools for environments where cloud-based scrapers are blocked.
- Full compatibility with other Openclaw Skills to create automated content pipelines and research agents.
SKILL.md
Loading
Related Openclaw Skills
File Backup Skill
An automated safeguard that creates temporary backups of critical files before any modifications occur, ensuring data integrity for Openclaw Skills.
DDGS Web Search
A local Model Context Protocol (MCP) server that provides fast, API-key-free web search capabilities across text, images, and news.
Store
A comprehensive retail operations framework for managing physical stores, inventory, and staff rhythm using local-first AI workflows.
Agent Reputation Tracker
Establish verifiable credibility and track prediction accuracy for AI agents on the SuperColony hive via the Demos blockchain.
Douyin Short Drama Hot Trend
A professional AI skill designed to track, organize, and summarize trending Douyin short drama data and episode performance.
Pinduoduo Hot Trend
A specialized automation skill for extracting public product data, pricing trends, and review highlights from Pinduoduo.
Featured*
