Can I use this skill to handle scanned PDF documents?

Yes, the skill includes specific workflows for using pytesseract and pdf2image to convert scanned PDF pages into searchable text.

Is it possible to extract tables to Excel?

Absolutely. The skill includes a guide for using pdfplumber to extract tables into Pandas DataFrames and exporting them directly to Excel files.

Which Python libraries does this skill support?

This skill provides implementation patterns for pdfplumber (extraction), pypdf (manipulation), reportlab (creation), and pytesseract (OCR).

Can I add passwords or watermarks to my PDFs?

Yes, the skill provides Python code snippets for merging watermark layers and encrypting PDFs with user and owner passwords.

Does this skill support command-line PDF tools?

Yes, it covers powerful CLI utilities like qpdf for merging/splitting and poppler-utils (pdftotext) for fast text extraction.

PDF Processing & Manipulation

Name: PDF Processing & Manipulation
Author: jawhnycooke

byjawhnycooke

•

コンテンツ管理

Manipulates PDF files through programmatic extraction, creation, merging, and OCR using Python and command-line utilities.

The PDF Processing skill empowers Claude to handle complex document workflows directly within your development environment. By leveraging powerful libraries like pdfplumber, pypdf, and reportlab, it enables automated text and table extraction, document merging and splitting, and even OCR for scanned documents. Whether you need to convert reports to Excel, generate dynamic PDFs from scratch, or automate form filling, this skill provides the patterns and toolsets required to integrate professional PDF handling into your applications and scripts.

主な機能

014 GitHub stars

02Document security management including password protection and watermarking.

03Seamless merging, splitting, and page-range extraction using pypdf and qpdf.

04Programmatic PDF generation with custom layouts and styles using ReportLab.

05OCR capabilities for converting scanned images into searchable text via Tesseract.

06Advanced text and table extraction to structured formats like Excel and Pandas.

ユースケース

01Automating the extraction of financial data from PDF invoices into structured spreadsheets.

02Building automated document pipelines that watermark, merge, or rotate files based on triggers.

03Generating dynamic PDF reports, invoices, or certificates directly from application data.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jawhnycooke/claude-plugins pdf

For use in Claude.ai and ChatGPT

Download Skill