pdf-reader

Extract text, images, tables, and metadata from PDF documents.

Updated Jan 22, 2026
One-click install
npx skills add https://github.com/tomlupo/ai-playground --skill pdf-reader-tomlupo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-reader
Source: https://github.com/tomlupo/ai-playground/tree/main/.claude/skills/pdf-skill
Command: npx skills add https://github.com/tomlupo/ai-playground --skill pdf-reader-tomlupo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fitz, Pillow, tabula, pandas, numpy, sentence-transformers, spacy, nltk, langdetect, transformers, torch, pdfminer.six, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PDF documents are rich but often unstructured; manual extraction and analysis is time-consuming and error-prone. The pdf-reader skill automates text, image, table extraction, NLP analysis, and metadata retrieval to turn PDFs into structured, searchable data.

Core Features & Use Cases

  • Text & image extraction: Retrieve full text and embedded images for indexing or processing.
  • Table extraction & NLP: Extract tabular data and run NLP analyses like entity recognition, summarization, or classification.
  • Language & metadata insights: Detect document language, obtain metadata, and summarize content for quick triage.
  • Use Case: Analyze hundreds of invoices by extracting line items and key fields, then classify and summarize for reporting.

Quick Start

Use the pdf-reader skill to extract text and images from a sample.pdf. Then run an NLP analysis to identify entities and summarize content for a compact overview.

Frequently Asked Questions about pdf-reader

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

FAQPage Schema
How do I extract text and images from PDF documents for data analysis?

To extract text and tables from PDF documents, use tools like PyMuPDF and Tabula to retrieve full content and parse tabular data. This converts unstructured PDFs into searchable text and structured dataframes ready for indexing or downstream data analysis workflows.

Can I extract tables from PDFs and run NLP entity recognition on the same document?

Yes, you can extract tables from PDFs and run NLP entity recognition on the same document. Using Tabula for table parsing alongside spaCy and transformers, you can extract structured line items and simultaneously perform named entity recognition or text classification tasks.

What is the best way to automate invoice processing and extract line items from PDF files?

The best way to automate invoice processing and extract line items from PDF files is combining table extraction with NLP analysis. You can parse tabular data using Tabula, then apply transformers to classify and summarize key extracted fields for automated reporting workflows.

Does PyMuPDF support language detection and metadata retrieval for research papers?

Yes, PyMuPDF supports language detection and metadata retrieval for research papers. Combined with langdetect, it can extract document metadata and identify the dominant language, allowing you to summarize content for quick triage and efficient document digitization.

How do I parse tabular data from PDFs when the layout is complex and unstructured?

To parse tabular data from PDFs with complex layouts, use Tabula and Pandas to extract structured dataframes. These libraries handle unstructured document layouts by identifying table boundaries and converting them into structured arrays for downstream analysis.