pdf

Extract text and tables from PDFs using Python libraries.

Updated Oct 22, 2025

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

Ready to run

npx skills add https://github.com/lemu/sea-prototype-template --skill pdf-lemu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/lemu/sea-prototype-template/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/lemu/sea-prototype-template --skill pdf-lemu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF workflows are tedious and error-prone, requiring manual extraction, reformatting, and re-assembly of documents across systems.

Core Features & Use Cases

Text and table extraction from PDFs for data pipelines and archiving.
Merge, split, rotate, watermark, and create new PDFs to support document processing workflows.
Use Case: Process hundreds of invoices by extracting totals and key fields, then compiling results into CSV.

Quick Start

Provide a PDF file and ask the AI to extract text or to merge multiple PDFs into a single document.

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 PDF files for a data pipeline?▼

To extract text and tables from PDF files, this skill automates parsing using Python libraries like pdfplumber and pypdf. It transforms unstructured PDF documents into actionable data suitable for pipelines, archiving, or compiling into CSV files.

Can I use Python to merge, split, or create new PDF documents?▼

Yes, you can use Python to merge, split, rotate, watermark, and create new PDF documents. This skill supports document processing workflows by relying on pypdf to manipulate and re-assemble PDF streams for archiving and reporting.

Does this PDF processing skill support OCR for scanned documents?▼

Yes, this PDF processing skill supports OCR for scanned documents. It uses pdf2image to render PDF streams into images, enabling OCR and image extraction to automate data extraction from scanned reports or invoices.

What is the best way to automate processing hundreds of PDF invoices?▼

The best way to automate processing hundreds of PDF invoices is using this skill's extraction and validation scripts. It reads PDFs, extracts totals and key fields, and compiles the results into a structured CSV output.

Do I need pypdf and pdfplumber installed to fill PDF forms?▼

Yes, you need pypdf and pdfplumber installed to fill PDF forms. This skill relies on these Python dependencies to parse, validate, and manipulate PDF streams, including scripts specifically for form filling and output generation.