Agent skill · data analytics · claude-office-skills
pdf-extraction
Extract text, tables, and metadata from PDFs using pdfplumber
Why this skill is useful
Provides specific commands and patterns for extracting structured data from PDFs using pdfplumber that the AI wouldn't reliably generate on its own.
What it needs
Requires pdfplumber installed locally. About 6k tokens when loaded. Last updated 2026-01-31. 363 stars on the source repository.
What this skill does
PDF Extraction Skill Overview This skill enables precise extraction of text, tables, and metadata from PDF documents using pdfplumber - the go-to library for PDF data extraction. Unlike basic PDF readers, pdfplumber provides detailed character-level positioning, accurate table detection, and visual debugging. How to Use 1. Provide the PDF file you want to extract from 2. Specify what you need: text, tables, images, or metadata 3. I'll generate pdfplumber code and execute it Example prompts: "Extract all tables from this financial report" "Get text from pages 5-10 of this document" "Find and extract the invoice total from this PDF" "Convert this PDF table to CSV/Excel" Domain Knowledge pdfplumber Fundamentals PDF Structure Text Extraction Basic Text Advanced Text Options Character-Level Access Table Extraction Basic Table Extraction Advanced Table Settings Table Finding Visual Debugging Cropping and Filtering Crop to Region Filter by Position Filter by Font Metadata and Structure Best Practices 1. Debug Visually: Use toimage() to understand PDF structure 2. Tune Table Settings: Adjust tolerances for your specific PDF 3. Handle Scanned PDFs: Use OCR first (this skill is for native text) 4. Process Page by Page: For large PDFs, avoid loading all at once 5. Check for Text: Some PDFs are images - verify text exists Common Patterns Extract All Tables to DataFrames Extract Specific Region Multi-column Layout Examples Example 1: Financial Report Table Extraction Example 2: Invoice Data Extraction Example 3: Resume/CV Parser Limitations Cannot extract from scanned/image PDFs (use OCR first) Complex layouts may need manual tuning Some PDF encryption types not supported Embedded fonts may affect text extraction No direct PDF editing capability Installation Resources pdfplumber Documentation Table Extraction Guide Visual Debugging
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills claude-office-skills/pdf-extraction