pdf

Name: pdf
Availability: InStock
Author: moritalous

Extract text and tables from PDFs and fill forms using Python libraries.

11|Updated Dec 27, 2025

Search Tags:#automation #pdf #form filling #text extraction #Python #PDF processing #PDF creation

Ready to run

npx skills add https://github.com/moritalous/claude-code-on-agentcore --skill pdf-moritalous

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/moritalous/claude-code-on-agentcore/tree/main/backend/assets/claude-agent/app/.claude/skills/pdf
Command: npx skills add https://github.com/moritalous/claude-code-on-agentcore --skill pdf-moritalous

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive toolkit for PDF processing, enabling automated text and table extraction, PDF creation and merging, and robust form handling to reduce manual document work.

Core Features & Use Cases

Automated PDF text and table extraction from native or scanned documents using Python libraries.
Form filling and annotation-based data entry for both fillable and non-fillable PDFs.
PDF creation, merging, and manipulation to assemble reports, invoices, and archives; supports end-to-end workflows.
Use case example: batch process invoices to extract key fields and automatically populate a CSV, or auto-fill client intake forms from structured data.

Quick Start

Start by selecting a sample PDF, run the field extraction workflow, and then fill fields with your data to generate a completed 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 a PDF automatically?▼

Automated PDF text and table extraction uses Python libraries like pypdf, pdf2image, and Pillow to parse and render documents. This captures content from native or scanned files, converting unstructured pages into editable data for administrative workflows.

Can I auto-fill PDF forms from structured data?▼

Auto-filling PDF forms from structured data is supported through annotation-based data entry. This handles both fillable and non-fillable PDFs, enabling automated completion of client intake forms and invoices without manual document work.

Does pypdf support merging and creating new PDF documents?▼

Yes, pypdf supports merging and creating new PDF documents. Combined with Pillow and pdf2image for rendering, it allows you to assemble reports, generate invoices, and manipulate existing PDFs to build end-to-end document archives.

What's the best way to batch process invoices and extract fields to a CSV?▼

Batch processing invoices to extract fields and populate a CSV requires Python libraries like pypdf for parsing. This automated workflow digitizes documents, extracts key data, and exports structured results for administrative archiving.

Do I need Python to automate PDF form filling and text extraction?▼

Yes, you need Python to automate PDF form filling and text extraction. The workflow relies on Python libraries including pypdf, pdf2image, and Pillow to parse, render, and generate documents from your files.

Can I render and process scanned PDFs using pdf2image and Pillow?▼

Yes, you can render and process scanned PDFs using pdf2image and Pillow. These Python libraries convert PDF pages into images, facilitating text extraction, table parsing, and form handling from scanned documents for digitization.