pdf

Extract text, tables, and images from PDFs using Python tools.

1|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/daxiangnaoyang/lobster-bot --skill pdf-daxiangnaoyang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/daxiangnaoyang/lobster-bot/tree/main/skills/skills/pdf
Command: npx skills add https://github.com/daxiangnaoyang/lobster-bot --skill pdf-daxiangnaoyang

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF processing tasks can be tedious and error-prone when handling forms, text, tables, and images across many documents. This skill provides a unified toolkit for reading, merging, splitting, rotating, watermarking, creating, encrypting/decrypting, OCR for scanned PDFs, and form handling.

Core Features & Use Cases

  • Read and extract text, tables, and images from PDFs.
  • Merge/split/rotate PDFs, apply watermarks, and create new PDFs.
  • Fill forms and encrypt/decrypt PDFs; suitable for automating document workflows.

Quick Start

Ask it to extract text from a PDF file.

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?

To extract text and tables from a PDF, you can use Python tooling like pdfplumber and pypdf. These libraries read structured data directly from documents, enabling automated text and table extraction for downstream processing workflows.

Can I perform OCR on scanned PDFs to extract text?

Yes, you can perform OCR on scanned PDFs using pdf2image and Pillow. This approach converts PDF pages into images, allowing Optical Character Recognition to extract text from scanned administrative and archival documents effectively.

Does this PDF automation approach support filling forms and adding watermarks?

Yes, this PDF automation approach supports filling forms and adding watermarks. Using pypdf, you can programmatically fill interactive form fields, apply watermarks, and merge documents to automate administrative document workflows.

What is the best way to merge, split, and rotate PDF documents?

The best way to merge, split, and rotate PDF documents is using Python libraries like pypdf. It provides robust programmatic control to manipulate page orientations and combine or divide documents with validation and error handling.

How do I handle PDF encryption and decryption safely?

To handle PDF encryption and decryption safely, use pypdf to apply or remove password protection. Ensure robust automation by including validation and error handling across diverse documents to prevent workflow interruptions.

What Python libraries do I need to extract images from a PDF?

To extract images from a PDF, you need Python libraries such as pdfplumber and Pillow. These dependencies work together to parse document structures and process embedded images for automated data extraction workflows.