pdf

Extract text, tables, images, and form data from PDF files.

5|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/tiancaiamao/ai --skill pdf-tiancaiamao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/tiancaiamao/ai/tree/main/skills/pdf
Command: npx skills add https://github.com/tiancaiamao/ai --skill pdf-tiancaiamao

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Handles repetitive PDF work that is tedious to do by hand, including reading content, editing documents, and producing finished files.

Core Features & Use Cases

  • Extract text, tables, metadata, and images from PDF documents.
  • Merge, split, rotate, watermark, encrypt, and create PDFs from scratch.
  • Fill form fields or add annotations to fillable and non-fillable forms, including scanned documents with OCR when needed.
  • Use case: turn a stack of invoices, applications, or reports into searchable, structured, and ready-to-share documents.

Quick Start

Ask the AI to process the attached PDF and specify whether you want extraction, form filling, OCR, merging, splitting, or annotation.

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?

To extract text and tables from PDF files, this solution uses pdfplumber and pypdf to parse content, metadata, and form data. It processes both native text layers and scanned pages requiring OCR.

Can I fill form fields and add annotations to scanned PDFs?

Yes, you can fill form fields and add annotations to fillable and non-fillable PDFs, including scanned documents. It applies OCR via pdf2image and PIL to handle non-fillable scanned pages with coordinate validation.

What's the best way to merge, split, or watermark PDF files?

The best way to merge, split, rotate, watermark, and encrypt PDFs is by using this solution's script components powered by pypdf. It handles document transformations and generates newly edited PDF outputs.

Does pdfplumber work with pypdf for invoice processing?

Yes, pdfplumber works with pypdf for invoice processing workflows. This combination extracts structured text, tables, and metadata from PDF documents, turning stacks of invoices into searchable, ready-to-share files.

Do I need Python libraries to perform OCR on scanned PDF pages?

Yes, you need Python libraries including pdf2image and PIL to perform OCR on scanned PDF pages. These dependencies convert scanned document images into searchable, structured text during the extraction workflow.