pdf

Process PDFs by extracting text, tables, merging, splitting, rotating, watermarking, encrypting, and filling forms.

Updated May 9, 2026
One-click install
npx skills add https://github.com/HwFee/AgentProject --skill pdf-hwfee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/HwFee/AgentProject/tree/main/skills/pdf
Command: npx skills add https://github.com/HwFee/AgentProject --skill pdf-hwfee

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF handling and analysis tasks are tedious and error-prone when done manually; this skill provides automated tooling to read, extract, merge, split, rotate, watermark, encrypt, and fill PDFs.

Core Features & Use Cases

  • Automated PDF processing across documents such as text extraction, table extraction, merging, splitting, page rotation, watermarking, and encryption.
  • Form handling: fillable forms and non-fillable forms using programmatic field annotation and editing.
  • Use Case: For example, process hundreds of invoices in PDF to extract invoice numbers, dates, totals, and compile into a CSV.

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 a PDF automatically?

To extract text and tables from a PDF, this automation uses pypdf and pdfplumber to parse document content, isolating structured table data and raw text for downstream analysis.

Can I fill out both fillable and non-fillable PDF forms programmatically?

Yes, you can fill both fillable and non-fillable PDF forms programmatically; the tool applies flexible field annotation and editing with validation to handle diverse document structures without manual input.

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

The best way to merge, split, and watermark PDFs is through automated document processing scripts that handle page rotation and annotation across files to ensure consistent output.

Does this PDF processing tool support rendering pages as images?

Yes, PDF processing supports rendering pages as images by relying on pdf2image and Pillow to parse, render, and annotate documents, transforming page content into image formats for visual workflows.

How do I process hundreds of invoice PDFs to extract dates and totals?

Processing hundreds of invoice PDFs to extract dates and totals is handled by automated text and table extraction, which reads unstructured document data and compiles the specific fields into a structured CSV file.