Pulls tables out of PDFs and images and converts them into CSV, Excel, or JSON. Handles both digital PDFs and does OCR on images, which is handy when you're dealing with scanned documents or screenshots. It'll auto-detect table boundaries and process multiple tables across entire documents. The repo shows 60 stars and 123 installs, so it's being used but not exactly battle-tested at scale. If you're tired of manually copying data from PDF reports or need to programmatically extract tabular data from documents, this does the job without requiring you to wire up your own OCR pipeline.
npx skills add https://github.com/dkyazzentwatwa/chatgpt-skills --skill table-extractor