skills.rest
varlabz
varlabzOFFICIAL
Explore all skills by this author →
GitHub

convert-to-markdown

Convert files, URLs, and YouTube videos into Markdown text.

Updated Apr 30, 2026
Search Tags:#pdf#markdown#web scraping#conversion#markitdown#youtube transcript#mhtml
One-click install
npx skills add https://github.com/varlabz/skills --skill convert-to-markdown-varlabz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: convert-to-markdown
Source: https://github.com/varlabz/skills/tree/main/convert-to-markdown
Command: npx skills add https://github.com/varlabz/skills --skill convert-to-markdown-varlabz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, yt-dlp, httpx, and includes scripts (resource) components.

What problem does it solve? Extracting readable text from PDFs, Office documents, web pages, MHTML archives, images, audio, and YouTube videos requires different tools for each format. This Skill routes each input type to the right converter and returns clean Markdown. ## Core Features & Use Cases - Universal file conversion: Convert PDF, DOCX, PPTX, XLSX, CSV, JSON, XML, EPUB, images, and audio to Markdown via MarkItDown. - YouTube transcript extraction: Download and clean subtitles from any YouTube URL or video ID, with language selection and metadata output. - Web page and MHTML conversion: Fetch live pages through a Crawl4AI server or parse saved MHTML archives into Markdown. - Use Case: A researcher needs to quote a YouTube lecture and a PDF whitepaper in their notes. They pass the video URL and the PDF path, and receive clean Markdown text from both. ## Quick Start Ask the agent to convert a file or URL to Markdown, for example: convert ./reports/quarterly.pdf to Markdown or get the transcript from this YouTube link.

Frequently Asked Questions about convert-to-markdown

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

FAQPage Schema
How do I convert a PDF or Word document to Markdown?▼

Run uvx markitdown on the file path to convert PDF, DOCX, PPTX, XLSX, and other formats to Markdown. The command preserves headings, lists, and tables in the output structure.

How to extract a transcript from a YouTube video?▼

Use the youtube-transcript script with a YouTube URL or video ID. It downloads subtitles via yt-dlp, cleans the VTT markup, and supports language selection with --lang and metadata output with --info.

Can I convert a live web page to Markdown without Crawl4AI?▼

Yes, fall back to downloading the page with curl and then running uvx markitdown on the saved HTML file. The Crawl4AI server on localhost:11235 is only needed for the full fetch-and-convert pipeline.

Does markitdown work on scanned PDFs or images?▼

MarkItDown runs OCR on images, so scanned PDFs can be processed by treating them as images. However, password-protected files cannot be decrypted and must be unlocked first.

Why does YouTube transcript extraction fail for some videos?▼

Age-restricted videos cause yt-dlp to fail with no workaround. Videos without any subtitles or auto-generated captions also return an error since no transcript source exists.

Related Skills

Explore More Content & Communication Skills→
capaas2capaas2

image-fetcher

Fetch visual assets via web search, Playwright screenshots, and user files.

Community
Intermediate
Clay-HHKClay-HHK
1

llamaindex

Build RAG pipelines with document ingestion, vector indexing, and query engines.

Community
Intermediate
neverpreparedneverprepared

youtube-harvester

Extract YouTube transcripts and metadata with timestamped chunking for vector retrieval.

Official
Advanced
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate