Agent skill · software engineering · aiskillstore
Comprehensive PDF manipulation, extraction, and generation with support for text extraction, form filling, merging, splitting, annotations, and creation. Use when working with .pdf files for: (1) Extracting text and tables, (2) Filling PDF forms, (3) Merging/splitting PDFs, (4) Creating PDFs programmatically, (5) Adding watermarks/annotations, (6) PDF metadata management
Why this skill is useful
Adds specific commands and workflows for PDF manipulation that the AI wouldn't reliably generate on its own.
What it needs
Requires pdf2image, pdfplumber, pillow, pymupdf, pypdf, pytesseract, reportlab installed locally. About 6k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
PDF Manipulation Skill Comprehensive guide for working with PDF files in Python, covering extraction, manipulation, creation, and advanced operations using progressive disclosure for efficiency. Core Capabilities Extract and manipulate PDF content: Extract text with layout preservation Extract tables and parse structured data Fill PDF forms programmatically Merge multiple PDFs into a single document Split PDFs by pages or ranges Create PDFs from scratch with text, images, and graphics Add watermarks and annotations Extract and modify metadata (author, title, keywords) Add password protection and encryption Perform OCR on scanned documents Convert images to PDF Compress and optimize PDF files Extract images from PDFs Rotate and reorder pages Quick Start Install required libraries: For detailed installation instructions including system dependencies, see: Library Installation Guide Python Libraries Overview pypdf: Basic operations (merge, split, rotate, metadata) pdfplumber: Advanced text/table extraction with layout awareness reportlab: Create PDFs from scratch (reports, invoices, documents) PyMuPDF (fitz): Advanced manipulation, annotations, compression pdf2image: Convert PDF pages to images (requires poppler) pytesseract: OCR for scanned documents (requires tesseract) Text Extraction Workflow Basic Extraction Layout-Aware Extraction Extract from Specific Region For detailed text extraction methods including OCR fallback and encoding handling, see: Text Extraction Reference Table Extraction Workflow Extract All Tables Advanced Table Detection For detailed table extraction strategies and data cleaning, see: Table Extraction Reference PDF Form Operations Fill Form Fields Extract Form Field Names For form filling, flattening, and debugging, see: PDF Operations Reference Merging and Splitting Merge PDFs Merge with Page Ranges Split into Individual Pages For merging with bookmarks and splitting by size, see: PDF Operations Reference Creating PDFs Simple Text PDF Styled R …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/pdf--a0a084