cyberneticlibrary

Convert documents to markdown

markitdownskillsetup L227,559
K-Dense-AI/scientific-agent-skills
What it does

Convert documents, web content, video transcripts to clean Markdown for LLM ingestion

Best for

Bulk document ingestion for RAG when format diversity requires unified conversion.

Inputs
  • · Source: PDF, HTML, DOCX, image, video URL, YouTube transcript
Outputs
  • · Clean Markdown with structured headings, tables, code blocks, links
Requires
  • · LLM/Claude API
  • · Bash/CLI
  • · Vault/Obsidian
  • · HTTP/REST API
  • · Git/GitHub
  • · Runtime (Python/Node)
Preconditions
  • · Source accessible (local file or public URL)
  • · Optional: Python 3.8+
Failure modes
  • · Complex layouts (sidebars, footnotes) flatten to linear text
  • · Embedded images described as alt-text only
  • · Tables converted to markdown may lose formatting hints
Trust signals
  • · Handles EPUB, audio, YouTube natively
  • · GitHub integration (README conversions)