markitdown

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

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/dotruru/claudemd --skill markitdown-dotruru
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/dotruru/claudemd/tree/main/skills/markitdown
Command: npx skills add https://github.com/dotruru/claudemd --skill markitdown-dotruru

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, markitdown, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

MarkItDown reduces the manual effort to convert diverse file formats into clean, token-efficient Markdown, enabling easier editing, searchability, and AI-ready content.

Core Features & Use Cases

  • Converts PDFs, DOCX, PPTX, XLSX, HTML, JSON, XML, CSV, ZIP, EPUBs, YouTube transcripts, and images (with OCR) into Markdown.
  • AI-assisted image descriptions and optional integrations (OpenRouter/AI, Azure Document Intelligence) to enrich content.
  • Batch processing and plugin support for scalable, automated document workflows.

Quick Start

Convert a sample PDF to Markdown to verify output.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDFs and Office documents to Markdown?

Converting PDFs and Office documents to Markdown relies on document conversion processes that transform varied file formats into clean, token-efficient text. This approach supports DOCX, PPTX, and XLSX files.

Does converting images to Markdown require OCR?

Converting images to Markdown requires OCR to extract text from image files. AI-assisted image descriptions further enrich this content through optional OpenRouter or OpenAI integrations.

Can I process multiple files in a batch document conversion workflow?

Batch processing supports scalable and automated document conversion workflows for multiple files. This method allows simultaneous transformation of varied formats into Markdown-ready output.

Do I need OpenAI to extract YouTube transcripts into Markdown?

Extracting YouTube transcripts into Markdown does not require OpenAI, as core document conversion handles web content natively. Optional OpenAI or OpenRouter integration enriches content with AI descriptions.

What is the best way to convert EPUB and HTML files for AI-ready content?

The best way to convert EPUB and HTML files for AI-ready content is using document conversion techniques that produce token-efficient Markdown. This output ensures easier editing and improved searchability.

Are there limitations when using plugins for document conversion?

Limitations when using plugins for document conversion may arise from dependency management and specific file formats. Robust error handling manages these edge cases during streaming and batch workflows.