Convert local files and URLs into clean Markdown.
npx skills add https://github.com/MisLink/agentry --skill markitdown-mislink
Please help me install this Agent Skill. Skill: markitdown Source: https://github.com/MisLink/agentry/tree/main/agents/.agents/skills/markitdown Command: npx skills add https://github.com/MisLink/agentry --skill markitdown-mislink
Markitdown automates converting diverse content—PDFs, Word docs, HTML pages, images (with OCR/EXIF), audio transcripts, ZIP archives, RSS feeds, YouTube transcripts, and more—into readable Markdown, eliminating tedious manual extraction and reformatting for AI workflows.
Convert a local file or URL to Markdown using markitdown.
High-intent search queries and answers about installing and using this skill.
Markitdown converts local PDF files or URLs into clean Markdown suitable for AI-friendly reading and analysis. It preserves structure and key metadata to enable reliable downstream tasks like research and summarization.
Markitdown extracts YouTube transcripts and RSS feeds into Markdown, transforming dynamic web content into readable text. It applies a deterministic workflow with intelligent fallbacks to web_fetch when parsing is noisy or non-textual.
Markitdown is the best way to convert DOCX, PPTX, and XLSX files for AI workflows because it automates cross-format content conversion into clean Markdown. It eliminates tedious manual extraction and reformatting while preserving document structure.
Yes, this content conversion tool supports extracting text from images via OCR and EXIF metadata, as well as generating audio transcripts. It converts these diverse formats into clean Markdown suitable for reading and analysis.
You can process HTML pages and ZIP archives by providing their local file paths or URLs to markitdown. It converts these diverse content types into clean Markdown, applying fallbacks to web_fetch when appropriate to handle noisy or non-textual parsing.
When converting EPUB and web content to Markdown, limitations may arise from noisy or non-textual parsing, though markitdown applies intelligent fallbacks to web_fetch to mitigate this. It is designed for deterministic cross-format conversion but relies on the original content's extractable text.
jackspaceConvert PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, and images into Markdown.
valtterimelkkoExtract clean markdown content from web pages using trafilatura.
nieomylniejaConvert web pages from URLs into clean Markdown using html-to-markdown-node.
tassiovaleConvert PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, and EPubs to Markdown.
