Capture a scanned document (PDF or image) into text, classify what it is, and route it to the right follow-up workflow. This is the front door for any scan the user drops in — after-visit summaries, lab results, receipts, letters, contracts, statements. OCRs natively on macOS (Vision framework as the core engine; an optional pdftotext fast-path when that binary happens to be present), classifies the document from the recognized text, and either hands off to a specialized handler skill (e.g. medical-records for an after-visit summary) or does a generic vault capture when no handler matches. Use when the user says 'scan this', 'OCR this', 'capture/archive this document', 'w…
