Are command-line tools supported for PDF tasks?

Yes, the skill includes quick reference commands for high-performance CLI utilities like qpdf for merging/splitting and poppler-utils for text extraction.

Which Python libraries does this skill support?

The skill primarily leverages pypdf for structural tasks, pdfplumber for data extraction, and reportlab for document creation.

How do I merge multiple PDFs into a single file?

The skill provides optimized Python scripts using PdfWriter as well as one-liner qpdf commands to merge multiple files efficiently.

Does it handle scanned PDFs?

While the core libraries focus on digital PDFs, the skill provides patterns for OCR workflows by converting pages to images and using pytesseract.

Can I extract tables from PDFs using this skill?

Yes, it includes specific implementation patterns for using pdfplumber to accurately extract tabular data into structured formats like pandas DataFrames.

PDF Processing & Manipulation

Name: PDF Processing & Manipulation
Author: plurigrid

byplurigrid

•

数据科学与机器学习

Facilitates comprehensive PDF manipulation, including text and table extraction, merging, splitting, and document generation using Python and CLI tools.

This skill provides a complete toolkit for handling PDF files within the Claude Code environment, enabling sophisticated document processing workflows. It equips the assistant with established patterns for extracting complex data like tables using pdfplumber, performing structural operations such as merging and splitting with pypdf, and generating dynamic documents from scratch with reportlab. By integrating both Python libraries and high-performance command-line utilities like qpdf, it serves as a versatile resource for data science preprocessing, automated report generation, and administrative document management.

主要功能

01Programmatic PDF generation and document design using reportlab

02Advanced text and tabular data extraction from complex PDF layouts

032 GitHub stars

04Integration with CLI utilities like qpdf and poppler-utils for batch processing

05Support for OCR workflows to handle scanned document conversion

06Structural PDF operations including merging, splitting, and page rotation

使用场景

01Automating the assembly of customized PDF documentation from disparate sources

02Extracting financial data or tables from multi-page reports into structured formats

03Batch processing and cleaning PDF archives for data analysis pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add plurigrid/asi pdf

For use in Claude.ai and ChatGPT

Download Skill