skills.rest
nex-agi
nex-agiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

pdf

Extract text, tables, and metadata from PDF documents.

195|32|Updated Nov 12, 2025
Search Tags:#ocr#document processing#data extraction#pdf#python#form filling#document automation#pdf manipulation
One-click install
npx skills add https://github.com/nex-agi/NexAU --skill pdf-nex-agi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/nex-agi/NexAU/tree/main/examples/code_agent/skills/document-skills/pdf
Command: npx skills add https://github.com/nex-agi/NexAU --skill pdf-nex-agi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually processing PDF documents for data extraction, form filling, or structural changes is a time-consuming and error-prone task. This Skill automates these operations, freeing up valuable time and ensuring accuracy.

Core Features & Use Cases

  • Intelligent Form Filling: Automatically fill both fillable and non-fillable PDF forms using visual analysis and precise annotations.
  • Advanced Data Extraction: Extract text, structured tables, and metadata from complex PDFs, including scanned documents via OCR.
  • Comprehensive Document Manipulation: Merge, split, rotate, watermark, and password-protect PDF files programmatically.
  • Use Case: A finance department receives hundreds of invoices monthly. This skill can automatically extract key financial data, organize it into a spreadsheet, and then merge all invoices into a single, searchable archive, drastically reducing manual data entry.

Quick Start

Use the pdf skill to extract all text from the attached file 'invoice-q3.pdf'.

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 automatically?▼

Text and table extraction from PDFs is automated using pdfplumber and pytesseract for OCR on scanned documents. The Skill reads multi-page PDFs, identifies structured data, and outputs extracted content as machine-readable text or tables without manual copying.

Can I automatically fill PDF forms without manual data entry?▼

Yes. The Skill fills both fillable and non-fillable PDF forms using visual analysis and JSON field mappings. It validates bounding boxes and applies data programmatically, eliminating manual form completion across batch workflows.

What's the best way to process scanned invoices and extract financial data?▼

Scanned invoices are processed via OCR using pytesseract and pdf2image to convert images to text. The Skill then extracts key financial data, metadata, and structured tables, enabling batch automation for invoices received in high volume.

How do I merge, split, and manipulate multiple PDF files in a batch workflow?▼

PDF manipulation—merging, splitting, rotating, watermarking, and password-protecting—is performed programmatically using pypdf. The Skill handles multi-page documents in batch mode, producing organized archives or restructured output files.

Does this work with both fillable and non-fillable PDF forms?▼

Yes. The Skill supports both fillable forms using field annotations and non-fillable forms using visual bounding-box analysis. It applies the same JSON field-mapping approach to either format, ensuring consistent automation regardless of form type.

What file formats and OCR capabilities does PDF processing support?▼

The Skill processes PDF files and scanned image-based PDFs. OCR support via pytesseract enables text extraction from scanned documents. Output formats include text, tables, merged PDFs, and annotated documents using Python tooling.

Related Skills

Explore More Data & Analytics Skills→
labs21-devlabs21-dev
28

pdf

Automate PDF creation, editing, extraction, OCR, form filling, and conversion.

Official
Advanced
weirdgmeweirdgme
4

platform-engineering

Design and implement scalable platform engineering patterns for internal developer platforms.

Community
Advanced
georgiymarchenkovgeorgiymarchenkov

Excel Analysis

Analyze Excel spreadsheets with pandas to extract structured insights and generate charts.

Community
Intermediate
TheWatcher01TheWatcher01

pdf

Automate PDF extraction, merging, and form filling with Python tooling.

Community
Advanced