batch-paper-pdf-to-markdown

Batch convert local PDFs to Markdown by processing entire directories or file lists, which generates per-PDF Markdown files alongside a dedicated image directory containing downloaded figures for knowledge bases.

Converting PDFs to Markdown preserves embedded images by downloading them into a corresponding folder and rewriting image references to relative paths like paper/imgs/..., ensuring portable document sharing and offline access.

You can process a whole folder of PDFs into Markdown at once by passing a directory path to the batch processing skill, which handles input validation and generates individual Markdown files and image outputs for each file.

If a PDF file is missing or an API error occurs during batch conversion, the skill provides robust error handling with options to either continue processing the remaining files or stop the batch operation immediately upon failure.

PaddleOCR is utilized for extracting text and images from PDFs into Markdown, supporting the conversion process by recognizing document content and enabling the generation of Markdown files with corresponding image directories.