reading-pdf

Extract text from PDF documents using pdftotext with pypdf fallback.

1|Updated Apr 12, 2026

Search Tags:#summarization #pdf #qa #pypdf #document-processing #text-extraction #pdftotext

Ready to run

npx skills add https://github.com/fascari/ai-config --skill reading-pdf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reading-pdf
Source: https://github.com/fascari/ai-config/tree/main/skills/reading-pdf
Command: npx skills add https://github.com/fascari/ai-config --skill reading-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reading PDFs often requires manual copying or OCR for scanned documents. This Skill provides a reliable way to extract readable text from PDFs using Poppler's pdftotext as the primary tool, with pypdf as a fallback when Poppler is unavailable, enabling downstream summarization and question-answering.

Core Features & Use Cases

Layout-aware text extraction: preserves word boundaries and handles multi-column layouts for readable output.
Fallback extraction: automatically switches to pypdf if pdftotext is not installed.
Text-driven tasks: supports summarization, QA, and content analysis on extracted text.

Quick Start

Provide a PDF path or attach a file to extract and present its text content.

Frequently Asked Questions about reading-pdf

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

FAQPage Schema

How do I extract text from a PDF for summarization?▼

The tool extracts text from PDFs using pdftotext as the primary method, preserving word boundaries and multi-column layouts. It outputs readable text directly ready for downstream summarization and question-answering tasks.

What is the best way to handle text extraction from encrypted PDFs?▼

Handling text extraction from encrypted PDFs involves prompting for the password. The extraction process retries with the appropriate password option, enabling pdftotext or the pypdf fallback to access secured document content.

Does PDF text extraction work if pdftotext is not installed?▼

PDF text extraction works without pdftotext installed. The system automatically falls back to pypdf, ensuring you can still extract text from PDFs and perform document processing without Poppler.

Can I use pypdf instead of pdftotext for document processing?▼

You can use pypdf for document processing as it serves as the fallback extraction tool. While pdftotext is primary for layout-aware text extraction, pypdf ensures text-driven tasks like QA remain functional.

Why does my PDF text extraction fail on scanned documents?▼

PDF text extraction may fail on scanned documents because this tool extracts embedded text rather than performing OCR. It relies on pdftotext or pypdf to read existing text layers, not recognize images.