markitdown

Convert PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, images, and audio into Markdown.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/viniruggeri/applied-dynamical-systems --skill markitdown-viniruggeri
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/viniruggeri/applied-dynamical-systems/tree/main/.agents/skills/markitdown
Command: npx skills add https://github.com/viniruggeri/applied-dynamical-systems --skill markitdown-viniruggeri

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, openai, requests, python-dotenv, 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 document formats into Markdown, enabling stable, machine-friendly text for analysis, review, and AI workflows.

Core Features & Use Cases

  • Converts PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, images (with OCR), and audio (with transcription) into Markdown
  • Supports optional AI-enhanced image descriptions and transcription via OpenRouter and Azure Document Intelligence
  • Ideal for research, data extraction, literature reviews, and publication-ready documentation

Quick Start

Convert a sample document to Markdown to see the 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 Word documents to Markdown for AI workflows?

Converting PDFs, DOCX, and other formats to Markdown is done by transforming diverse documents into clean, machine-friendly text. This enables stable text for analysis, review, and AI workflows without tedious manual formatting.

What file formats are supported for Markdown document conversion?

Markdown document conversion supports PDFs, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, images, and audio. Images use OCR for text extraction, while audio files use transcription to generate Markdown text.

Do I need OpenRouter or Azure Document Intelligence to convert documents to Markdown?

OpenRouter and Azure Document Intelligence are optional dependencies for AI-enhanced features like image descriptions and audio transcription. Basic document conversion to Markdown works without these additional services.

How do I extract text from PDFs and slides for research and literature reviews?

Extracting text from PDFs and PPTX slides produces clean Markdown suitable for research and literature reviews. Converting these formats enables stable text extraction for data analysis and publication-ready documentation.

Can I automate document conversion for spreadsheets and presentations into Markdown?

Automating document conversion for XLSX spreadsheets and PPTX presentations into Markdown is fully supported. The process transforms structured slide and spreadsheet data into clean, machine-friendly text for downstream analysis.

What is the best way to convert images and audio files into Markdown text?

Converting images and audio to Markdown text is best handled through OCR and transcription capabilities. Optional AI-enhanced image descriptions and audio transcription via OpenRouter provide accurate Markdown output.