Skip to content
Kitbay
Submit
Skill

convert-pdf-to-md

MITUpdated on Nov 11, 202641,032GitHub starsIncludes scripts

A skill in GitHub's awesome-copilot collection that has the agent turn PDF files into Markdown before answering questions about them, summarising them or pulling out data.

What the skill teaches

A skill in GitHub's awesome-copilot collection that has the agent turn PDF files into Markdown before answering questions about them, summarising them or pulling out data. A bundled Python script uses Microsoft's MarkItDown for text and tables and PyMuPDF to save the embedded images, writing one folder per document, and it can process a whole folder of PDFs. A reference file walks through installing Python, markitdown and pymupdf. For folders that mix file types, the skill tells the agent to run its sibling skills for Word and Excel files at the same time so none are skipped.

Capabilities

  • Convert PDF files to Markdown with MarkItDown
  • Extract embedded images with PyMuPDF
  • Batch-convert a folder of PDFs