pdf

Extract text and tables from PDFs into text, CSV, or Excel.

2|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/mammut001/pipi-shrimp-agent --skill pdf-mammut001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/mammut001/pipi-shrimp-agent/tree/main/src-tauri/skills/pdf
Command: npx skills add https://github.com/mammut001/pipi-shrimp-agent --skill pdf-mammut001

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill automates common PDF tasks such as extracting text and tables, creating and merging documents, and handling forms, enabling rapid, error-free processing of PDFs at scale.

Core Features & Use Cases

  • Extract text and tables from PDFs into usable formats (text, CSV, or Excel).
  • Create new PDFs and perform batch merges or splits to manage large collections of documents.
  • Fill in and annotate forms (fillable and non-fillable) to automate digitization and distribution workflows.
  • Use cases include processing invoices, reports, and forms in bulk, archival data extraction, and automated document preparation.

Quick Start

Extract text and tables from a PDF by running the tool on document.pdf and saving outputs to text.txt.

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 in bulk?

You can extract text and tables from PDFs by running the provided scripts on local documents, which parse content using pypdf and output usable formats like text or CSV for rapid bulk processing.

Can I fill out and annotate non-fillable PDF forms automatically?

Yes, the skill fills and annotates both fillable and non-fillable PDF forms automatically using Python scripts, enabling form digitization and automated document distribution workflows without manual data entry.

Does pypdf support batch merging and splitting for large PDF collections?

Yes, pypdf supports batch merging and splitting for large PDF collections. The skill creates new PDFs and performs batch operations to manage large document sets locally without external services.

What's the best way to convert PDF pages to images for validation?

The best way to convert PDF pages to images for validation is using pdf2image with Pillow. The skill renders PDF pages into images locally to validate outputs and ensure accurate document processing.

Do I need an internet connection to process sensitive PDF documents locally?

No, you do not need an internet connection. The skill performs fast, local PDF processing and form handling entirely on your machine, leveraging Python libraries to parse and modify documents securely.