skills.rest
svpfahad
svpfahadCOMMUNITY
Explore all skills by this author →
GitHub

markitdown

Convert PDF, Office documents, images, and audio files to Markdown format.

Updated Jun 18, 2026
Search Tags:#ocr#document processing#markdown#literature review#openrouter#pdf conversion#batch conversion
One-click install
npx skills add https://github.com/svpfahad/RES200 --skill markitdown-svpfahad
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/svpfahad/RES200/tree/main/claude-scientific-writer-main/.claude/skills/markitdown
Command: npx skills add https://github.com/svpfahad/RES200 --skill markitdown-svpfahad

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Converting documents like PDFs, Word files, PowerPoint slides, and spreadsheets into clean, LLM-friendly Markdown is tedious and error-prone when done manually. This Skill automates the conversion of 15+ file formats into token-efficient Markdown suitable for analysis, note-taking, and AI workflows. ## Core Features & Use Cases - Multi-Format Conversion: Convert PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, EPUB, and YouTube URLs to Markdown. - AI-Enhanced Image Descriptions: Use vision models via OpenRouter (Claude, GPT-4o, Gemini) to generate detailed descriptions of figures and slides during conversion. - Batch & Literature Processing: Parallel batch conversion scripts and a scientific literature converter that extracts metadata, organizes papers by year, and generates index files. - Use Case: Convert a folder of research paper PDFs into organized Markdown files with front matter metadata and an auto-generated index for a literature review. ## Quick Start Convert the attached research paper PDF to Markdown using the markitdown skill and save the result as a .md file.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert a PDF to Markdown in Python?▼

Install markitdown with pip install 'markitdown[pdf]', then create a MarkItDown instance and call md.convert("file.pdf"). The result's text_content attribute contains the Markdown output, which you can print or write to a file.

What file formats does MarkItDown support?▼

MarkItDown supports PDF, DOCX, PPTX, XLSX, XLS, images (JPEG, PNG, GIF, WebP with OCR), audio (WAV, MP3 with transcription), HTML, CSV, JSON, XML, ZIP archives, EPUB e-books, Outlook MSG files, and YouTube video transcripts.

How do I convert PowerPoint slides with AI image descriptions?▼

Pass an OpenAI-compatible client pointed at OpenRouter and a vision model like anthropic/claude-sonnet-4.5 to MarkItDown via llm_client and llm_model parameters. Set the OPENROUTER_API_KEY environment variable, then convert the PPTX file normally.

Does MarkItDown work with scanned PDF documents?▼

Yes, but OCR support requires installing Tesseract on your system (brew install tesseract on macOS or apt-get install tesseract-ocr on Ubuntu). For complex layouts, Azure Document Intelligence provides enhanced extraction via the docintel_endpoint parameter.

Why does MarkItDown conversion fail with a missing dependency error?▼

MarkItDown organizes dependencies into optional feature groups, so the base install lacks format support. Install the specific extra you need, such as pip install 'markitdown[pdf]' for PDFs or 'markitdown[all]' for every format.

How do I batch convert multiple documents to Markdown?▼

Use the batch_convert.py script with an input and output directory, optionally filtering by extensions and enabling parallel workers. For example, python scripts/batch_convert.py papers/ output/ --extensions .pdf .docx --workers 4 converts files in parallel.

Related Skills

Explore More Education & Research Skills→
NEXUZ-SYSNEXUZ-SYS

image-fetcher

Acquire web images, Playwright screenshots, and user files into a reference folder.

Official
Intermediate
Chanw-researchChanw-research
38

academic-researcher

Analyze research papers and draft literature reviews with citations.

Official
Advanced
gabrielvuksanigabrielvuksani

scientific-schematics

Generate publication-quality scientific diagrams from natural-language descriptions with quality review.

Community
Intermediate
NousResearchNousResearch
227.8k

ocr-and-documents

Extract text and structured data from PDFs, scanned documents, and images.

Official
Intermediate