Introduction
This skill covers reading, creating, splitting, merging, rendering, and validating PDF files. It selects native tools or libraries according to the task, extracts text, tables, and page information, and renders generated output back to images to inspect clipping, overlap, fonts, and pagination. For scanned documents, OCR uncertainty is stated explicitly.
Use Cases
Use it for papers and reports, table extraction, PDF merging, page reordering, document conversion, annotation review, and pre-delivery visual checks. It verifies both textual correctness and whether the final pages are actually readable.
Template
Provide the PDF, page range, requested operation, layout that must be preserved, output filename, and quality requirements. The output includes the processed PDF, needed text or tables, rendered previews, and validation notes.
