Skip to content
UsecaseBoard
← All use cases
githubbuilder

Give a document agent a PDF table-extraction and OCR playbook

At a glance

Anthropic's published PDF skill supplies tool recipes for reading tables, OCR of scanned pages, combining outputs, and producing files, giving an agent concrete operations for document work. This workflow is listed under builder, claude-skills, pdf, ocr, table-extraction.

Agents / tools
Claude, Anthropic PDF skill, pdfplumber, Tesseract

Building a tool for these workflows? See weekly rates.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

Use the PDF skill in a compatible Claude agent and provide a copy of a document containing both digital tables and scanned pages. Ask it to select table extraction or OCR per page, export a combined workbook, and keep page references. Compare sample rows against the originals and flag unreadable cells.
Explore all →