skills.rest
Mathews-Tom
Mathews-TomCOMMUNITY
Explore all skills by this author →
𝕏@tom_mathewsGitHub

to-markdown

Convert files and URLs to Markdown using MarkItDown with OCR and transcription.

310|45|Updated Feb 22, 2026
Search Tags:#ocr#pdf#markdown#playwright#trafilatura#markitdown#document-ingestion
One-click install
npx skills add https://github.com/Mathews-Tom/praxis-skills --skill to-markdown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-markdown
Source: https://github.com/Mathews-Tom/praxis-skills/tree/main/skills/to-markdown
Command: npx skills add https://github.com/Mathews-Tom/praxis-skills --skill to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Converts diverse file types and web content into clean, LLM-friendly Markdown to make documents searchable, ingestible, and readable without manual cleanup or format-specific tooling.

Core Features & Use Cases

  • Wide format support: Handles PDF, DOCX, PPTX, XLSX, HTML, images (EXIF + OCR), audio (transcription), CSV/JSON/XML, YouTube, EPUB, and more.
  • Robust fetch strategies: Uses trafilatura for static pages and Playwright for JS-rendered content, with YouTube transcript handling and escalation paths for paywalls and scanned PDFs.
  • Workflow-ready output: Produces Markdown files or inline content optimized for RAG, knowledge bases, and LLM pipelines with rules for tables, headings, and post-processing.
  • Error handling & escalation: Detects empty extractions, suggests OCR or Azure Document Intelligence, and warns on protected or paywalled content.

Quick Start

Convert the file /tmp/report.pdf to Markdown and save the output as /tmp/report.md.

Frequently Asked Questions about to-markdown

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

FAQPage Schema
How do I convert PDF files to Markdown for RAG pipelines?▼

You can convert PDFs to Markdown by applying the MarkItDown engine, which transforms documents into clean, LLM-friendly text with proper headings and tables optimized for knowledge base ingestion.

Can I extract text from images using OCR and output Markdown?▼

Yes, the Skill handles image files by applying OCR escalation paths to extract text and output clean Markdown content suitable for document ingestion and LLM summarization.

Does this tool fetch and convert JS-rendered HTML pages to Markdown?▼

Yes, the tool fetches JS-rendered HTML pages using Playwright and static pages using trafilatura, converting both into clean Markdown for downstream RAG workflows.

What is the best way to convert YouTube transcripts and audio into Markdown?▼

The best way is using this Skill's dedicated YouTube transcript handling and audio transcription features, which produce workflow-ready Markdown output optimized for summarization.

How do I handle empty extractions or paywalled content when converting URLs?▼

When converting URLs, the Skill detects empty extractions and warns on protected or paywalled content, suggesting escalation paths like Azure Document Intelligence for processing.

What file formats are supported when converting documents to Markdown?▼

Supported formats include PDF, DOCX, PPTX, XLSX, HTML, images, audio, CSV, JSON, XML, and EPUB, covering diverse content types for RAG preparation and knowledge base ingestion.

Related Skills

Explore More Content & Communication Skills→
fmoda3fmoda3
42

arxiv-to-md

Convert arXiv TeX sources into clean Markdown documents preserving equations and references.

Community
Intermediate
xukrutdonutxukrutdonut

docstrange

Convert PDFs and images to Markdown, JSON, CSV, or HTML with confidence scores.

Community
Basic
DbillionaerDbillionaer
1

rag-engineer

Design and optimize RAG systems with semantic chunking and hybrid search.

Community
Advanced
anilcan-karaanilcan-kara

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf or marker-pdf.

Community
Intermediate