Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.
$npx -y skills add abruptive/ankh.md --skill ocr-and-documentsInstalls into the current project.
Run `npx skills use "https://github.com/abruptive/ankh.md" --skill "abruptive/ankh.md/ocr-and-documents"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/abruptive/ankh.md" that are relevant to the current task. Run `npx skills add "https://github.com/abruptive/ankh.md"` and select the relevant skills, then follow their instructions.