skills.rest
HaykTarkhanyan
HaykTarkhanyanCOMMUNITY
Explore all skills by this author →
GitHub

markitdown

Convert PDFs, DOCX, PPTX, XLSX, HTML, CSV, and more into Markdown text.

Updated Mar 31, 2026
Search Tags:#documents#pdf#markdown#docx#convert#ai-descriptions
One-click install
npx skills add https://github.com/HaykTarkhanyan/dst_research --skill markitdown-hayktarkhanyan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/HaykTarkhanyan/dst_research/tree/main/.claude/skills/markitdown
Command: npx skills add https://github.com/HaykTarkhanyan/dst_research --skill markitdown-hayktarkhanyan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MarkItDown consolidates the tedious process of turning diverse document formats into clean Markdown, enabling faster preparation for reviews, data extraction, and model-friendly content.

Core Features & Use Cases

  • Format coverage: Converts PDFs, DOCX, PPTX, XLSX, images (with OCR), HTML, CSV, JSON, XML, ZIP, EPUBs, YouTube URLs, and more.
  • AI-assisted descriptions: Optional AI-generated descriptions for visuals to enhance scientific and technical documents.
  • Extensible workflows: Supports optional directories (scripts, references, assets) and plugins for Azure DI and AI integrations to tailor the pipeline.

Quick Start

To start, provide a file path to a supported document and call the conversion function to generate Markdown text.

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 text?▼

To convert PDF and DOCX files to Markdown text, you provide the document file path to the conversion function, which automates extraction and outputs clean Markdown ready for review or data processing.

Can I extract text from images and image-based PDFs?▼

Extracting text from images and image-based PDFs requires optional OCR tooling dependencies. The conversion pipeline supports multimedia inputs to generate Markdown, provided the OCR environment is properly configured.

Does converting media-rich documents support AI descriptions?▼

Converting media-rich documents supports optional AI-generated descriptions for visuals. This requires OpenAI or OpenRouter dependencies to enhance scientific and technical document extraction with contextual image summaries.

What is the best way to process academic papers and corporate documents for AI models?▼

The best way to process academic papers and corporate documents for AI models is converting them into clean Markdown. This creates model-friendly content, enabling faster preparation for data extraction and content processing.

What document formats are supported when converting files to Markdown?▼

Supported document formats for Markdown conversion include PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, ZIP, EPUBs, and YouTube URLs, covering a broad range of academic and corporate file types.

Why do I need optional dependencies like OpenAI for document conversion?▼

Optional dependencies like OpenAI are needed for document conversion to enable AI-driven image descriptions. Without them, the core conversion works, but multimedia and visual context extraction in technical documents is limited.

Related Skills

Explore More Content & Communication Skills→
JuanMS20JuanMS20

github-auth

Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.

Community
Intermediate
Blake-JohnBlake-John

pymupdf

Convert PDF documents into Markdown, JSON, and text for LLM workflows.

Community
Intermediate
trungkiet2005trungkiet2005

markitdown

Convert diverse document formats to Markdown for AI processing.

Community
Advanced
attentiondotnetattentiondotnet

ocr-and-documents

Extract text from PDFs, DOCX, PPTX, and scanned documents via OCR.

Community
Intermediate