pdf-extraction

The pdf-extraction skill provides tools for extracting text, tables, and metadata from PDF documents using the pdfplumber library. It supports character-level positioning, table detection, and visual debugging for native text PDFs.

7.0K
Installs
5
Use cases
9/10
Quality

Is pdf-extraction safe to install?

Review before installing

Review before installing: our audit of pdf-extraction's source files found 2 shell commands, 0 external URLs, file reads and writes (medium risk). Every command and URL listed appears verbatim in the skill's source. The skill reads local PDF files and writes local image files for debugging and Excel files for data export.

How we audit skills: our security review methodology.

Who is this skill for?

Users needing to extract structured data from PDF documents, including financial reports, invoices, and resumes.

What can you do with it?

  • Extracting tables from financial reports into CSV or Excel formats
  • Parsing invoice data like invoice numbers, dates, and totals
  • Extracting specific sections from resumes
  • Visual debugging of PDF structures using bounding boxes
  • Filtering text by font, size, or page region

How good is this skill?

Quality score: 9/10. The skill documentation is comprehensive, providing clear code examples for common extraction tasks and debugging. It explicitly states limitations regarding scanned PDFs.

What does the skill file contain?

SKILL.md
# 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 th...

Frequently asked questions

Does this skill support scanned PDFs?

No. The skill is designed for native text PDFs. Scanned PDFs require an OCR step before processing.

Can I extract specific regions of a page?

Yes. The skill supports cropping pages using bounding boxes defined by (x0, top, x1, bottom) coordinates.

How do I debug table extraction issues?

The skill provides visual debugging tools like `im.debug_tablefinder()` to draw detected objects and save them as images.

Data sourced from claude-office-skills/skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills