markitdown

Convert PDFs, Word, PPTX, Excel, HTML, EPUB, and images to Markdown.

5|2|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/hyperbolic-c/auto-writing --skill markitdown-hyperbolic-c
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/hyperbolic-c/auto-writing/tree/main/claude-scientific-writer/skills/markitdown
Command: npx skills add https://github.com/hyperbolic-c/auto-writing --skill markitdown-hyperbolic-c

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MarkItDown eliminates the tedious, error-prone task of converting diverse file formats into clean, Markdown outputs, enabling researchers and teams to feed content into LLMs and analysis pipelines with consistent structure.

Core Features & Use Cases

  • Converts PDFs, Word, PPTX, Excel, HTML, EPUB, images (with OCR), audio (transcription), YouTube transcripts, and ZIP archives to Markdown.
  • AI-enhanced image descriptions via OpenRouter-powered models for scientific figures, diagrams, and slides.
  • Azure Document Intelligence support for complex layouts and improved table extraction.
  • Batch processing and scripting utilities for automation, data pipelines, and literature workflows.
  • Suitable for researchers, educators, content teams, and developers building data-driven documentation workflows.

Quick Start

Install MarkItDown and run a basic conversion, e.g. convert a file like research_paper.pdf to Markdown. Use AI-enhanced descriptions by supplying an OpenRouter model when desired.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert a PDF to Markdown for LLM processing?

You can convert PDFs to Markdown by running the MarkItDown conversion script, which transforms documents into LLM-friendly text. It supports batch processing to streamline feeding content into scientific workflows and analysis pipelines.

How does AI image description work during document conversion?

AI-enhanced image descriptions are powered by OpenRouter models during the conversion process. This feature generates text descriptions for scientific figures, diagrams, and slides, ensuring visual data is captured in the Markdown output.

Can I use Azure Document Intelligence to improve table extraction?

Yes, Azure Document Intelligence integration is supported optionally to improve layout analysis and table extraction. This handles complex document structures, ensuring tables are accurately converted into Markdown format.

What file formats can I batch convert to Markdown?

You can batch convert PDFs, Word, PPTX, Excel, HTML, EPUB, images, audio, YouTube transcripts, and ZIP archives to Markdown. This automation supports data pipelines and literature workflows for researchers and developers.

Do I need an OpenRouter API key to convert files to Markdown?

An OpenRouter API key is only required if you want to utilize AI-enhanced descriptions for images and figures. Basic document conversion to Markdown works without it, relying on standard OCR and text extraction.

Does this tool transcribe audio files into Markdown text?

Yes, the document conversion process supports audio transcription, converting spoken content into Markdown text. This allows you to easily feed audio data into LLMs and data-driven documentation workflows.