PDF Skill

Description

This skill enables comprehensive PDF manipulation including text extraction, form field reading, page merging/splitting, annotation, and metadata operations. Uses pdf-lib and pdf-parse libraries for reliable PDF processing.

Instructions

When the user asks you to work with PDF files, follow these patterns:

Reading & Extraction

Copy
const fs = require('fs');
const pdfParse = require('pdf-parse');

// Extract text from PDF
const dataBuffer = fs.readFileSync('document.pdf');
const data = await pdfParse(dataBuffer);
console.log(data.text);       // Full text content
console.log(data.numpages);   // Page count
console.log(data.info);       // Metadata (title, author, etc.)

Creating & Modifying PDFs

Copy
const { PDFDocument, rgb, StandardFonts } = require('pdf-lib');

// Create new PDF
const pdfDoc = await PDFDocument.create();
const page = pdfDoc.addPage([612, 792]); // Letter size
const font = await pdfDoc.embedFont(StandardFonts.Helvetica);

page.drawText('Hello World', {
  x: 50, y: 700,
  size: 24,
  font,
  color: rgb(0, 0, 0),
});

const pdfBytes = await pdfDoc.save();
fs.writeFileSync('output.pdf', pdfBytes);

Merging PDFs

Copy
const pdfDoc = await PDFDocument.create();
const pdf1 = await PDFDocument.load(fs.readFileSync('file1.pdf'));
const pdf2 = await PDFDocument.load(fs.readFileSync('file2.pdf'));

const pages1 = await pdfDoc.copyPages(pdf1, pdf1.getPageIndices());
const pages2 = await pdfDoc.copyPages(pdf2, pdf2.getPageIndices());

pages1.forEach(p => pdfDoc.addPage(p));
pages2.forEach(p => pdfDoc.addPage(p));

fs.writeFileSync('merged.pdf', await pdfDoc.save());

Extracting Form Fields

Copy
const pdfDoc = await PDFDocument.load(pdfBuffer);
const form = pdfDoc.getForm();
const fields = form.getFields();

fields.forEach(field => {
  const name = field.getName();
  const type = field.constructor.name;
  console.log(`${name} (${type})`);
});

Rules

• Always install dependencies first: npm install pdf-lib pdf-parse
• Use pdf-parse for text extraction (read-only operations)
• Use pdf-lib for creation, modification, and form operations
• Handle encrypted PDFs gracefully — inform user if password is needed
• For large PDFs (>50 pages), process page ranges to manage memory
• Always validate the PDF buffer before processing: check for %PDF header
• Write output files to the project directory, never overwrite originals unless asked

Examples

User: Extract all text from invoice.pdf Action: Use pdf-parse to read and return full text content

User: Merge these 3 PDFs into one Action: Use pdf-lib to copy pages from each source into a new document

User: Fill out this PDF form with my data Action: Load with pdf-lib, get form fields, set values, save