pdf

Extract text, tables, and metadata from PDFs using Python libraries.

Updated Feb 9, 2026

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

Ready to run

npx skills add https://github.com/lucasromanh/Voces-Cafayate --skill pdf-lucasromanh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/lucasromanh/Voces-Cafayate/tree/main/.agents/skills/pdf
Command: npx skills add https://github.com/lucasromanh/Voces-Cafayate --skill pdf-lucasromanh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDFs are a common source of information, but extracting text, tables, and metadata, merging or splitting documents, and applying edits can be tedious and error-prone. This skill provides a programmable toolkit to automate diverse PDF workflows end-to-end.

Core Features & Use Cases

Reading and extracting text, tables, and metadata from PDFs
Merging, splitting, rotating, watermarking, and creating PDFs
Filling forms (fillable and non-fillable), encrypting/decrypting, and OCR on scanned PDFs
Use cases include automating invoice processing, contract review, and archival tasks that produce structured outputs

Quick Start

Process a PDF by extracting all text and tables and saving the results to a separate text or CSV file.

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 documents to automate invoice processing?▼

You can extract text and tables from PDFs to automate invoice processing by applying this skill's Python toolkit, which reads document contents and saves structured outputs to text or CSV files without manual intervention.

Can I perform OCR on scanned PDFs to extract data from archival documents?▼

Yes, you can perform OCR on scanned PDFs to extract data from archival documents. The skill utilizes libraries like pdf2image and Pillow to process scanned images and retrieve actionable text from them.

What is the best way to merge, split, or fill forms in PDF files using Python?▼

The best way to merge, split, or fill forms in PDF files using Python is through this skill's automated workflows, which handle both fillable and non-fillable forms, alongside document merging and splitting operations.

Does this PDF processing approach work with administrative, legal, and research reports?▼

Yes, this PDF processing approach works with administrative, legal, and research reports. It applies end-to-end document workflows to extract metadata, text, and tables from various structured reports.

How do I encrypt, decrypt, or add watermarks to PDF files programmatically?▼

You can encrypt, decrypt, or add watermarks to PDF files programmatically by applying this skill's editing features, which allow diverse document modifications alongside core text and data extraction tasks.