markitdown

Convert PDFs, DOCX, PPTX, XLSX, and other files to Markdown.

6|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/ccam80/thesis-writer --skill markitdown-ccam80
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/ccam80/thesis-writer/tree/main/skills/markitdown
Command: npx skills add https://github.com/ccam80/thesis-writer --skill markitdown-ccam80

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 the tedious process of converting diverse file formats into clean, Markdown text optimized for AI workflows, literature reviews, and publication-ready outputs.

Core Features & Use Cases

  • Broad format support: PDFs, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, ZIP, YouTube transcripts, and images with OCR.
  • AI-enhanced conversions: Optional OpenRouter/OpenAI integration to generate image descriptions and figure captions for scientific content.
  • Batch processing and scripting: Included scripts for batch conversion, literature extraction, and index/catalog creation enable scalable workflows.
  • Use Case: Researchers can batch-convert an entire literature folder into Markdown, generate an index, and feed the results into a writing pipeline.

Quick Start

Basic usage demonstrates creating a MarkItDown instance and converting a file, then accessing the Markdown text. Example: md = MarkItDown(); result = md.convert("document.pdf"); print(result.text_content)

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 to Markdown for AI processing?

You can convert PDFs, DOCX, and other diverse file formats to Markdown by creating a conversion instance, processing the target file, and accessing the extracted text content. This prepares documents for AI-ready workflows.

Can I batch convert an entire folder of research literature to Markdown?

Yes, batch processing is supported through included scripts for literature extraction and index creation. You can scale workflows to convert entire folders of research documents into Markdown text.

Does this conversion tool support extracting text from images and YouTube transcripts?

Extracting text from images via OCR and pulling YouTube transcripts are both supported formats. These conversions turn visual and video content into Markdown text for research and writing workflows.

How do I generate image descriptions and figure captions for scientific PDFs?

AI-enhanced conversions use optional OpenRouter or OpenAI integration to generate image descriptions and figure captions. This specifically improves the Markdown output quality for scientific content.

What is the best way to prepare EPUB and XLSX files for a literature review?

The best way to prepare EPUB and XLSX files for a literature review is converting them into clean Markdown text. This standardizes diverse formats into a single, AI-ready output for analysis.

Do I need an OpenAI API key to convert HTML and JSON files to Markdown?

You do not need an OpenAI API key for basic conversion of HTML and JSON files. OpenRouter or OpenAI integration is only optional for AI-enhanced features like generating scientific image descriptions.