pdf

Extracts, fills, and transforms PDF documents for automation workflows.

52|8|Updated Mar 12, 2026

Search Tags:#automation #ocr #document processing #pdf #form filling #text extraction

Ready to run

npx skills add https://github.com/eddie-292/grapwork --skill pdf-eddie-292

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/eddie-292/grapwork/tree/main/frontend/skills/examples/pdf
Command: npx skills add https://github.com/eddie-292/grapwork --skill pdf-eddie-292

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the manual overhead of reading, filling, and transforming PDF documents by giving you a repeatable workflow for both editable forms and non-fillable files.

Core Features & Use Cases

Extract text, tables, metadata, and images from PDFs.
Fill fillable forms or place annotations on non-fillable documents after measuring labels and entry regions.
Merge, split, rotate, watermark, encrypt, or OCR documents for common office and archival workflows.
Example: turn a stack of scanned invoices into searchable PDFs and extract the fields you need for downstream processing.

Quick Start

Tell the pdf skill which PDF file to process and whether you want text extraction, form filling, or document transformation.

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 document for automation workflows?▼

PDF text and table extraction uses pdfplumber to parse structured content and pypdf to retrieve metadata, producing deterministic text outputs ready for downstream invoice or document processing. It handles both native and scanned files when paired with OCR.

Can I fill fillable PDF forms and add annotations to non-fillable scanned documents?▼

PDF form filling validates fillable fields using pypdf, while non-fillable documents are handled by measuring label regions with pdfplumber and pdf2image to place annotations precisely, generating completed forms for office and archival workflows.

What's the best way to OCR a stack of scanned invoices and extract specific fields?▼

Scanned invoice OCR and field extraction render pages with pdf2image and Pillow, then apply text recognition to create searchable PDFs and extract required fields, enabling batch document workflows for downstream processing.

Does this PDF processing approach support merging, splitting, and watermarking files?▼

PDF transformation supports merging, splitting, rotating, watermarking, and encrypting documents through pypdf operations, delivering processed files suitable for common office automation and archival requirements.

Do I need Python libraries like pypdf and pdfplumber to process PDF documents?▼

PDF document processing requires pypdf, pdfplumber, pdf2image, and Pillow to validate fields, render pages, extract content, and generate deterministic outputs for both fillable forms and scanned files.

Can I batch process multiple PDF files for text extraction and form filling?▼

Batch PDF workflows automate text extraction and form filling across multiple documents by applying deterministic processing logic to each file, yielding consistent outputs for invoice processing and archival systems.