skills.rest
rubensliv
rubenslivCOMMUNITY
Explore all skills by this author →
GitHub

markitdown

Convert diverse document formats to Markdown using Python libraries.

15|2|Updated Dec 17, 2025
Search Tags:#pdf#markdown#pptx#docx#openrouter#ai-descriptions#file-conversion
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill markitdown-rubensliv
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/markitdown
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill markitdown-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Quickly turning a wide range of file formats into clean, token-efficient Markdown for AI workflows and scientific writing, reducing manual formatting and extraction effort.

Core Features & Use Cases

  • Converts PDFs, DOCX, PPTX, XLSX, EPUB, HTML, CSV/JSON/XML, ZIPs, images (with OCR), and audio (transcription) into structured Markdown.
  • Enables AI-enhanced image descriptions via OpenRouter and optional Azure Document Intelligence for complex layouts.
  • Ideal for literature reviews, data extraction, and preparing documents for LLM-assisted drafting and publishing.

Quick Start

Install MarkItDown and run a basic conversion to Markdown from a sample file such as document.pdf.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDF and DOCX files to Markdown for AI workflows?▼

You can convert PDF and DOCX files to Markdown by using the MarkItDown core library, which automates extraction and formatting to produce clean, token-efficient text for AI-driven content preparation and research documentation.

What file formats can be converted to Markdown using Python libraries?▼

Supported formats include PDF, DOCX, PPTX, XLSX, EPUB, HTML, CSV, JSON, XML, ZIPs, images, and audio. It uses Python libraries to structure diverse documents into Markdown, applying OCR for images and transcription for audio.

Can I use OpenRouter or OpenAI to generate AI descriptions for images during file conversion?▼

Yes, AI-enhanced image descriptions are supported through optional OpenRouter and OpenAI integrations, allowing you to generate contextual text for images while converting documents into structured Markdown.

Does converting complex PDF layouts to Markdown require Azure Document Intelligence?▼

Complex PDF layouts require optional Azure Document Intelligence integration to accurately extract structured text, ensuring precise conversion of scientific workflows and literature review documents into Markdown format.

What is the best way to prepare scientific literature and data for LLM-assisted drafting?▼

The best way to prepare literature for LLMs is converting source files like PDFs, XLSX, and EPUB into clean Markdown. This reduces manual formatting effort and creates structured, token-efficient output for AI drafting.

Why does my Markdown file conversion not work for certain PDF documents?▼

Markdown conversion may fail on complex PDFs if the optional Azure Document Intelligence integration is not configured. Basic conversion relies on the core library, which may struggle with advanced layouts without it.

Related Skills

Explore More Education & Research Skills→
Zeyuyang-0420Zeyuyang-0420

markitdown

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

Community
Intermediate
inbharataiinbharatai
22

literature-reviewer

Summarize academic papers and extract key findings, gaps, and themes.

Community
Intermediate
hyperbolic-chyperbolic-c
5

markitdown

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

Community
Advanced
biomaps-infrabiomaps-infra

doc-markitdown

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

Official
Advanced