document-to-markdown

Convert PDFs, Office files, images, HTML, and URLs into Markdown.

Updated Aug 27, 2026

Search Tags:#pdf #markdown #rag #images #convert #urls #office

Ready to run

npx skills add https://github.com/kcchien/skills --skill document-to-markdown

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-to-markdown
Source: https://github.com/kcchien/skills/tree/main/document-to-markdown
Command: npx skills add https://github.com/kcchien/skills --skill document-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, pymupdf4llm, marker, paddleocr, paddlepaddle, pdf2image, surya, pytesseract, easyocr, opencc-python-reimplemented, pillow, lxml, prettytable, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Converts documents and URLs into clean Markdown for downstream LLM/RAG workflows, enabling consistent text extraction and content ingestion across tools.

Core Features & Use Cases

Converts PDFs, Office files, images, HTML and URLs to Markdown to support AI pipelines.
Supports batch processing, frontmatter metadata, and multiple backends (PyMuPDF4LLM, Marker, MarkItDown, PaddleOCR).
Real-world use: transform a folder of PDFs and web pages into a searchable Markdown knowledge base for agents.

Quick Start

Convert a local PDF or URL to Markdown using gateway.py with your preferred backends.

Frequently Asked Questions about document-to-markdown

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

FAQPage Schema

How do I convert PDFs and Office files to Markdown for RAG workflows?▼

You can convert PDFs and Office files to Markdown for RAG workflows by processing them through the gateway.py script, which extracts text and structures it for downstream indexing and knowledge-base creation.

Can I batch convert multiple URLs and PDFs to Markdown at once?▼

Yes, you can batch convert multiple URLs and PDFs to Markdown at once. The tool supports batch processing, allowing you to transform entire folders of documents and web pages into a searchable Markdown knowledge base.

Does converting PDF to Markdown support extracting text from images?▼

Converting PDF to Markdown does support extracting text from images by utilizing multiple OCR backends like PaddleOCR, Tesseract, and EasyOCR to ensure accurate text extraction from scanned documents and image files.

What is the best way to convert HTML pages to Markdown for LLM ingestion?▼

The best way to convert HTML pages to Markdown for LLM ingestion is using a conversion tool that cleans HTML structures into Markdown format, enabling consistent text extraction and content ingestion across tools.

Do I need Python 3.10 or higher to use this document to Markdown converter?▼

Yes, you need Python 3.10 or higher to use this document to Markdown converter. The environment requires this version to run the necessary dependencies and backends for processing documents and URLs.