PDF Processing

Extract text, tables, and images, manipulate page order, fill out interactive forms, and perform OCR on scanned PDFs.

Supported Operations

• Text & Table Extraction: Parse raw text, structured tables, and page layout metadata using pdfplumber and pypdf.
• Page Manipulation: Merge, split, rotate, crop, stamp watermarks, and reorder PDF pages via qpdf and pdftk.
• Form Filling: Read interactive PDF form fields, populate values programmatically, and flatten output fields.
• OCR Processing: Convert scanned raster PDFs into searchable text documents using pytesseract and pdf2image.

Installation

Add this skill to your workspace:

npx skills add https://github.com/anthropics/skills --skill pdf

Quick Start

Use standard Python snippets or CLI commands to inspect and extract PDF contents:

from pypdf import PdfReader

reader = PdfReader("sample.pdf")
print(f"Total Pages: {len(reader.pages)}")
text = reader.pages[0].extract_text()