pdf

Merge, split, extract text and tables, and OCR scanned PDFs.

Updated Aug 23, 2026

Search Tags:#ocr #data extraction #pdf #python #form filling #document management #pdf processing

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/RyoyaYahagi/skills/tree/main/pdf
Command: npx skills add https://github.com/RyoyaYahagi/skills --skill pdf-ryoyayahagi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

Manual PDF processing is tedious and error-prone; this skill automates common tasks such as merging, splitting, text and table extraction, OCR on scanned pages, form handling, and PDF creation.

Core Features & Use Cases

Merges, splits, rotates, and watermarks PDFs, and supports form filling workflows.
Extracts text and tables from PDFs (including OCR for scanned pages) and supports generating consolidated reports.
Use Case: Automate processing of batches of invoices by extracting key fields and compiling results into a single dataset.

Quick Start

Run a basic merge example to combine doc1.pdf and doc2.pdf into merged.pdf.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text and tables from a scanned PDF using Python?▼

To extract text and tables from a scanned PDF, this skill applies OCR on scanned pages using pytesseract and pdf2image, while pdfplumber handles native text and table extraction to produce structured data.

Can I automate batch processing of invoices to extract key fields from PDFs?▼

Yes, you can automate batch processing of invoices by applying Python scripts to extract key fields from multiple PDF files and compile the results into a single consolidated dataset.

What is the best way to merge, split, and watermark PDF documents in Python?▼

The best way to merge, split, and watermark PDFs is using this skill's automated workflows implemented with pypdf, which handle document modifications and generate updated PDF files.

Does this skill support filling out and generating PDF forms programmatically?▼

Yes, this skill supports form filling workflows and PDF creation programmatically, utilizing Python libraries like ReportLab alongside pypdf to read, modify, and generate interactive documents.

Do I need Pillow and pdf2image to perform OCR on scanned PDF pages?▼

Yes, performing OCR on scanned PDF pages requires pdf2image to convert pages into images and Pillow for image processing, before pytesseract extracts the text.

Why does pdfplumber fail to extract text from my scanned PDF document?▼

Pdfplumber fails to extract text from scanned PDFs because they contain images rather than embedded text; this skill resolves this by using pdf2image and pytesseract for OCR processing.