anthropics-pdf

Extract text and tables from PDFs using Python tools.

1|Updated Mar 15, 2026

Search Tags:#automation #ocr #pdf #form filling #text extraction #merge pdf

Ready to run

npx skills add https://github.com/family3253/skill --skill anthropics-pdf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: anthropics-pdf
Source: https://github.com/family3253/skill/tree/main/skills/anthropics-pdf
Command: npx skills add https://github.com/family3253/skill --skill anthropics-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDFs often require manual, repetitive operations such as extracting text, merging files, filling forms, or OCR for scanned pages. This skill provides a structured, scripting-based approach to perform these tasks reliably and repeatedly.

Core Features & Use Cases

Text extraction (text and tables) from PDFs, with optional OCR for scanned pages
Merge, split, rotate, and watermark PDFs; create new documents and encrypt/decrypt
Fill forms (fillable and non-fillable) and export extracted field data
Extract embedded images and automate end-to-end PDF workflows
Example: convert a batch of invoices to searchable text and consolidate them into a single report

Quick Start

Provide a PDF file and ask the AI to extract text, merge documents, or perform common PDF tasks.

Frequently Asked Questions about anthropics-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 in bulk?▼

To extract text and tables from PDF files, this skill uses pdfplumber and pypdf to parse multi-page documents and output structured data. It reliably handles batch extraction for developers and knowledge workers.

Can I perform OCR on scanned PDF pages to make them searchable?▼

Yes, you can perform OCR on scanned PDF pages. The skill leverages pdf2image and Pillow to convert document pages into images, enabling text extraction from scanned files that lack embedded text layers.

What is the best way to merge multiple PDFs into a single report?▼

The best way to merge multiple PDFs into a single report is using this skill's automated pypdf scripts. It programmatically combines separate files, such as a batch of processed invoices, into one consolidated document.

Does this approach support filling out forms in existing PDF documents?▼

Yes, this approach supports filling forms in existing PDF documents. It automates handling both fillable and non-fillable forms, and can also export extracted field data from multi-page files using pypdf.

How do I split, rotate, or watermark PDF files programmatically?▼

To split, rotate, or watermark PDF files programmatically, the skill provides structured Python scripts using pypdf. These automate document manipulation to produce reliable outputs for end-to-end workflows.