pdf

Extract text and tables from PDFs using Python libraries.

1|1|Updated Feb 9, 2026

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

Ready to run

npx skills add https://github.com/Randi-Agent/randi-agent --skill pdf-randi-agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/Randi-Agent/randi-agent/tree/main/src/skills/anthropic-repo/skills/pdf
Command: npx skills add https://github.com/Randi-Agent/randi-agent --skill pdf-randi-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow.

What problem does it solve?

PDF documents often require manual, repetitive operations such as text extraction, data gathering from forms, merging multiple files, or converting scanned pages into searchable text. This Skill automates common PDF tasks to save time and reduce errors.

Core Features & Use Cases

Text and table extraction: pull text, metadata, and tables from PDFs for downstream processing.
Document composition and editing: merge, split, rotate pages, add watermarks, encrypt or decrypt, and fill forms.
OCR for scans: convert scanned PDFs into searchable text using OCR workflows.
Automation workflows: batch-process invoices, reports, or archives with minimal manual steps.

Quick Start

Process PDFs by extracting text and tables, merging or splitting files, filling forms, and applying basic edits with Python libraries.

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 PDF for data processing?▼

Extracting text and tables from a PDF is done by parsing documents with pypdf and pdfplumber. This Skill automates pulling text, metadata, and table structures to provide clean data for downstream processing workflows.

What's the best way to automate filling forms and merging multiple PDF files?▼

Automating form filling and merging multiple PDF files is handled through document composition features using pypdf. You can merge, split, rotate pages, and fill forms with robust validation to process large document archives efficiently.

Can I convert scanned PDFs into searchable text using OCR?▼

Scanned PDFs can be converted into searchable text using OCR workflows. The Skill leverages pdf2image and Pillow to render scanned pages into images, enabling accurate text extraction from non-searchable documents.

Does this PDF processing approach work for batch processing invoices?▼

Batch processing invoices is fully supported through automation workflows that minimize manual steps. You can extract data from multiple invoice PDFs sequentially using pypdf and pdfplumber to automate repetitive data gathering tasks.

What Python libraries are needed to parse, render, and modify PDF documents?▼

Parsing, rendering, and modifying PDF documents requires Python libraries like pypdf, pdfplumber, pdf2image, and Pillow. These dependencies enable text extraction, document editing, and image-based processing for comprehensive PDF automation.

Why does text extraction fail on scanned PDF files and how to fix it?▼

Text extraction fails on scanned PDF files because the content is image-based rather than embedded text. You can fix this by applying OCR workflows with pdf2image and Pillow to render and scan pages for text recognition.