file-to-markdown

Convert documents, images, audio, web content, and structured data to Markdown.

Updated Oct 21, 2025
One-click install
npx skills add https://github.com/plipowczan/portfolio --skill file-to-markdown
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: file-to-markdown
Source: https://github.com/plipowczan/portfolio/tree/main/.claude/skills/file-to-markdown
Command: npx skills add https://github.com/plipowczan/portfolio --skill file-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill converts any file into markdown format, enabling easier reading, editing, and integration into markdown-based workflows. It supports documents, images (with OCR), audio (transcription), web content, and structured data, facilitating faster content processing and data capture.

Core Features & Use Cases

  • Wide format support: converts documents (PDF, DOCX, PPTX, XLSX), images (PNG/JPG/GIF) with OCR, audio (MP3/WAV) with transcription, and web/data formats to markdown.
  • OCR & transcription: extracts text from images and audio to searchable markdown.
  • Batch conversion: convert many files in a folder efficiently and consistently.
  • CLI and Python integration: use the provided scripts or the MarkItDown API to automate conversions in pipelines.

Quick Start

Use the convert_file.py script to convert a file, e.g., python convert_file.py report.pdf

Frequently Asked Questions about file-to-markdown

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

FAQPage Schema
How do I convert PDF documents to markdown format?

Convert PDF to markdown using the convert_file.py script with MarkItDown library support. The Skill extracts text, preserves headings and structure, and outputs clean, readable markdown while maintaining document formatting.

Can I extract text from images using OCR during conversion?

Yes, the Skill converts images (PNG, JPG, GIF) to markdown by running OCR extraction. Text from images becomes searchable markdown content integrated into your workflow.

Does this support batch conversion of multiple files at once?

Batch conversion is supported—process many files in a folder efficiently and consistently using the provided scripts. The Skill reports conversion results with clear status for each file.

What file formats can be converted to markdown?

Supported formats include documents (PDF, DOCX, PPTX, XLSX), images (PNG, JPG, GIF), audio (MP3, WAV), web content (HTML, MHTML), and structured data (CSV, JSON, XML)—all convert to markdown output.

How do I automate file-to-markdown conversion in my pipeline?

Use the MarkItDown API directly in Python or invoke the conversion scripts from your workflow. Automate single-file or batch conversions programmatically while preserving UTF-8 encoding and document structure.

Can I transcribe audio files and convert them to markdown?

Audio files (MP3, WAV) are transcribed and converted to markdown format. Transcription output becomes readable, searchable markdown content for your documentation or data workflows.