skills.rest
OpenLoaf
OpenLoafOFFICIAL
Explore all skills by this author →
GitHub

pdf-skill

Automates PDF read, write, convert, and OCR tasks including extraction, merging, splitting, and encryption.

94|9|Updated Dec 8, 2025
Search Tags:#ocr#pdf#convert#read#write#pdf-lib#pdfkit
One-click install
npx skills add https://github.com/OpenLoaf/OpenLoaf --skill pdf-skill-openloaf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-skill
Source: https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/pdf
Command: npx skills add https://github.com/OpenLoaf/OpenLoaf --skill pdf-skill-openloaf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

PDF documents are often scattered across tools for reading, editing, and converting. This Skill centralizes PDF operations to streamline documentation workflows, enabling you to extract data, fill forms, render pages as images, merge or split files, apply watermarks, rotate pages, encrypt/decrypt, and convert between PDF and other formats, all within your local AI environment.

Core Features & Use Cases

  • Read: extract text, tables, form-fields, images, and metadata with PdfInspect.
  • Write/Modify: create new PDFs or modify existing ones using JsSandbox with pdf-lib / pdfkit.
  • Convert & OCR: convert to/from docx/md/txt and OCR scans via CloudImageUnderstand, for scanned PDFs.
  • Use Case: You have multiple invoices in PDF — extract line items to a CSV, fill forms, and assemble a single consolidated document.

Quick Start

Load the pdf-skill and begin by inspecting a PDF with PdfInspect, then perform write or convert operations with JsSandbox as needed.

Frequently Asked Questions about pdf-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text and tables from a PDF document?▼

You can extract text and tables from a PDF by inspecting the document to read its structured content, metadata, and form fields. This process enables automated extraction of line items and tabular data for downstream workflows.

Can I convert a scanned PDF to a searchable text format?▼

Yes, you can convert scanned PDFs to searchable text formats by applying OCR to the document. This recognizes text within images, enabling conversion between PDF and formats like docx, markdown, or txt.

What is the best way to merge multiple PDF files and add a watermark?▼

The best way to merge multiple PDF files and add a watermark is by using local write operations to combine documents and apply overlays. This modifies existing PDFs programmatically without requiring external online services.

Does this approach support filling AcroForm fields in existing PDFs?▼

Yes, this approach supports filling AcroForm fields in existing PDFs. You can read form fields from a document and execute write operations to populate them, streamlining documentation and invoice processing workflows.

How do I rotate pages and encrypt a PDF locally?▼

To rotate pages and encrypt a PDF locally, you apply write operations using a JavaScript sandbox environment with libraries like pdf-lib. This enables secure document modification and encryption without uploading files externally.

Related Skills

Explore More Software Engineering Skills→
MarbleSodasMarbleSodas

ocr-and-documents

Extract searchable text from PDFs and scanned documents via web or local parsing.

Community
Intermediate
dkyazzentwatwadkyazzentwatwa
86

document-converter-suite

Convert documents between PDF, DOCX, PPTX, XLSX, TXT, CSV, MD, and HTML formats.

Community
Intermediate
ntaksh42ntaksh42
1

pdf-processor

Extract text, handle forms, and generate PDFs from HTML or Markdown.

Community
Intermediate
dobrinz123dobrinz123

pdf

Extracts text, tables, and metadata from PDF files.

Community
Advanced