Pdf skill

Skill ulpi-io/plugin-marketplace/plugins/404kidwiz/skills/pdf-skill

A curated collection of 7,800+ agent skills for Claude Desktop, sourced from skills.sh

Install

npx -y skills add ulpi-io/plugin-marketplace --skill pdf-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Expert in generating, parsing, and manipulating PDF documents using tools like PDFKit, PDF.js, and Puppeteer. Use when creating PDFs, extracting content, merging documents, or filling forms. Triggers include "PDF", "generate PDF", "parse PDF", "extract PDF", "merge PDF", "PDF form", "PDFKit".

SKILL.md

3.1 KB, 691 tokens by cl100k_base, as published. Nobody here has run it

PDF Skill

Purpose

Provides expertise in programmatic PDF generation, parsing, and manipulation. Specializes in creating PDFs from scratch, extracting content, merging/splitting documents, and handling forms using PDFKit, PDF.js, Puppeteer, and similar tools.

When to Use

Generating PDFs programmatically
Extracting text or data from PDFs
Merging or splitting PDF documents
Filling PDF forms programmatically
Converting HTML to PDF
Adding watermarks or annotations
Parsing PDF structure and metadata
Building PDF report generators

Quick Start

Invoke this skill when:

Generating PDFs from code or data
Extracting content from PDF files
Merging, splitting, or manipulating PDFs
Filling or creating PDF forms
Converting HTML/web pages to PDF

Do NOT invoke when:

Word document creation → use /docx-skill
Excel/spreadsheet work → use /xlsx-skill
PowerPoint creation → use /pptx-skill
General file operations → use Bash or file tools

Decision Framework

PDF Operation?
├── Generate from scratch
│   ├── Simple → PDFKit (Node) / ReportLab (Python)
│   └── Complex layouts → Puppeteer/Playwright + HTML
├── Parse/Extract
│   ├── Text extraction → pdf-parse / PyPDF2
│   └── Table extraction → Camelot / Tabula
├── Manipulate
│   └── pdf-lib (merge, split, edit)
└── Forms
    └── pdf-lib (fill) / PDFtk (advanced)

Core Workflows

1. PDF Generation with PDFKit

Install PDFKit (npm install pdfkit)
Create new PDDocument
Add content (text, images, graphics)
Style with fonts and colors
Add pages as needed
Pipe to file or response

2. HTML to PDF Conversion

Set up Puppeteer/Playwright
Navigate to HTML content or URL
Configure page size and margins
Set print options (headers, footers)
Generate PDF buffer
Save or stream result

3. PDF Parsing and Extraction

Choose parser (pdf-parse, PyPDF2, pdfplumber)
Load PDF file
Extract text or structured data
Handle multi-page documents
Clean and normalize extracted text
Output in desired format

Best Practices

Use vector graphics over raster when possible
Embed fonts for consistent rendering
Test PDF output across different readers
Handle large PDFs with streaming
Use appropriate library for task complexity
Consider accessibility (tagged PDFs)

Anti-Patterns

Anti-Pattern	Problem	Correct Approach
Image-only PDFs	Not searchable/accessible	Use text with fonts
No font embedding	Rendering issues	Embed required fonts
Memory loading large PDFs	Crashes	Stream processing
Ignoring encryption	Security/access issues	Handle encrypted PDFs
Wrong tool for job	Over-engineering	Match tool to complexity