Convert text, HTML, PDFs, EPUBs, images, YouTube transcripts, and URLs into Markdown with metadata.
npx skills add https://github.com/ojspace/md-anything --skill md-anything
Please help me install this Agent Skill. Skill: md-anything Source: https://github.com/ojspace/md-anything/tree/main Command: npx skills add https://github.com/ojspace/md-anything --skill md-anything
md-anything reduces the burden of transforming files, URLs, and media into clean Markdown for workflows and agents, keeping everything local-first.
Try converting a sample input with mda to generate Markdown immediately.
High-intent search queries and answers about installing and using this skill.
You can convert PDFs and HTML files to Markdown locally by using the mda CLI tool, which processes files offline by default and outputs structured Markdown with provenance and metadata.
Yes, you can extract YouTube transcripts and convert URLs to Markdown using the local-first mda CLI, which operates offline by default and optionally leverages remote fallbacks when network access is available.
Yes, md-anything supports batch processing for converting multiple files to Markdown via the ingest command, allowing you to process entire folders of notes, PDFs, or images into structured Markdown with chunk data.
The best way to integrate Markdown conversion into an agent workflow is through the local MCP server, which exposes a stable interface for tool consumers to convert files and URLs into Markdown with structured metadata.
You do not need an internet connection to convert EPUBs and images to Markdown, as md-anything is local-first by default, but it can optionally use remote fallbacks for certain conversions when network access is available.
aresbitSummarize URLs, local files, and video transcripts into concise summaries.
mikkelkrogsholmIngest PDFs, Markdown, HTML, and plain text into Bookstrap knowledge bases with semantic chunking and embeddings.
DingTalk-Real-AIScript DingTalk operations and batch-manage organizational data via CLI commands.
twjarviszyra-webExtract text, tables, and metadata from PDFs and scanned documents.
