markitdown

Converts PDFs, DOCX, PPTX, XLSX, images, audio, HTML, CSV, and more into Markdown via OCR, transcription, and AI image descriptions.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/LuizEduPP/skills --skill markitdown-luizedupp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/LuizEduPP/skills/tree/main/markitdown
Command: npx skills add https://github.com/LuizEduPP/skills --skill markitdown-luizedupp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MarkItDown streamlines converting diverse documents and media into Markdown so AI assistants can ingest and analyze content without manual retyping or format juggling.

Core Features & Use Cases

  • Broad Format Support: Converts PDFs, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, and YouTube URLs into Markdown with OCR and transcription.
  • AI-enhanced descriptions: Integrates OpenRouter/OpenAI models for image captions and leverages Azure Document Intelligence plus a plugin system to handle complex layouts.
  • Batch and research workflows: Provides scripts for batch conversion, literature review indexing, and AI-assisted image descriptions to prepare papers, presentations, and datasets for downstream analysis.

Quick Start

Ask MarkItDown to convert your latest PDF or DOCX file into Markdown so you can continue editing in plain text.

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 DOCX files into clean Markdown for LLM analysis?

Converting PDFs and DOCX files into Markdown requires format-specific workflows that extract text and layout elements. This process eliminates manual retyping by generating clean, LLM-friendly markup suitable for review or analysis sessions.

Can I extract text from audio recordings and images using Markdown transcription?

Yes, you can extract text from audio recordings and images using Markdown transcription workflows. These processes apply audio transcription and AI-generated image descriptions to convert multimedia content into clean, LLM-friendly markup.

Does converting spreadsheets and web archives into Markdown require Azure Document Intelligence?

Converting spreadsheets and web archives into Markdown does not strictly require Azure Document Intelligence, as standard converters handle basic extraction. Azure Document Intelligence is optional and used for complex layouts to ensure clean Markdown content.

What is the best way to batch convert research literature into Markdown?

The best way to batch convert research literature into Markdown is using dedicated batch-processing scripts. These scripts automate the extraction pipeline across multiple documents, producing clean markup for literature review indexing and downstream analysis.

Do I need an OpenAI API key to generate AI image descriptions during document conversion?

Yes, you need an OpenAI or OpenRouter model integration to generate AI image descriptions during document conversion. This dependency allows the system to automatically caption images and embed them within the final Markdown output.