markitdown

Convert documents, images, audio, and web content into Markdown.

4|1|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/rm2thaddeus/Aitor_Skills --skill markitdown-rm2thaddeus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/rm2thaddeus/Aitor_Skills/tree/main/markitdown
Command: npx skills add https://github.com/rm2thaddeus/Aitor_Skills --skill markitdown-rm2thaddeus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the conversion of a wide variety of file formats into Markdown, making content easily digestible and processable by LLMs.

Core Features & Use Cases

  • Universal Conversion: Supports over 15 file formats including PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, and EPubs.
  • AI-Enhanced Descriptions: Can generate detailed descriptions for images within documents using LLMs.
  • Use Case: Convert a complex research paper in PDF format, along with its embedded images and tables, into a clean Markdown document suitable for LLM analysis or documentation.

Quick Start

Use the markitdown skill to convert the file named 'report.docx' into a markdown file.

Frequently Asked Questions about markitdown

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDF, DOCX, and other documents to Markdown for LLM processing?

You can convert documents to Markdown by using this tool to process PDF, DOCX, PPTX, and XLSX files. It transforms complex document structures into clean Markdown text suitable for LLM analysis and documentation.

Can I extract text from images using OCR and generate AI descriptions?

Yes, converting images to Markdown includes OCR text extraction. It also offers AI-enhanced image descriptions using LLMs to generate detailed context for visual content within your documents.

Does this tool support transcribing audio files and converting YouTube URLs to Markdown?

Yes, converting audio files and YouTube URLs to Markdown is fully supported. It handles transcription for audio content and extracts text from YouTube links directly into Markdown format.

What is the best way to convert JSON, CSV, and XML data files into readable Markdown?

Converting structured data files like JSON, CSV, and XML to Markdown is handled natively. It parses these formats and outputs structured Markdown, making data easily digestible for downstream applications.

How does Azure Document Intelligence improve PDF conversion compared to standard processing?

Azure Document Intelligence integration provides advanced PDF processing capabilities. It enhances the extraction of complex elements from PDFs, ensuring higher accuracy when converting intricate layouts to Markdown.

Can I extract content from EPub files and HTML web pages into a single Markdown document?

Yes, converting EPub files and HTML web content to Markdown is supported. It parses both formats effectively, extracting readable text and structure into a unified Markdown output.