pdf-reading

Extract text, tables, images, attachments, and form fields from local PDFs.

112|26|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/Wide-Moat/open-computer-use --skill pdf-reading-wide-moat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-reading
Source: https://github.com/Wide-Moat/open-computer-use/tree/main/skills/public/pdf-reading
Command: npx skills add https://github.com/Wide-Moat/open-computer-use --skill pdf-reading-wide-moat

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of needing to read and extract information from PDFs whose content is not already available in your chat context, including text-heavy documents, scanned documents, slide-decks, tables, embedded images, attachments, and form fields.

Core Features & Use Cases

  • PDF content inventory & diagnostics: Identify page counts, metadata, whether text is extractable, embedded images, embedded files/attachments, and font encoding issues.
  • Text and layout-aware extraction: Extract text using tools like pypdf and pdftotext (layout mode) and pdfplumber for positioning-oriented extraction and tables.
  • Visual inspection via rasterization: Convert specific pages to images with pdftoppm for cases where charts, diagrams, equations, complex layout, or scans require visual understanding.
  • Embedded content extraction: Extract raster images with pdfimages, extract attachments with pdfdetach, and read interactive form field values with pypdf.
  • Decision guidance for the right strategy: Choose among text extraction, rasterization, and OCR fallback (for scanned PDFs) to match the document type and the question asked.

Quick Start

Ask the AI to inspect and extract the key fields from an attached PDF by first running a content inventory, then extracting readable text (and tables if present), and rasterizing only the necessary pages for any figures or garbled text.

Frequently Asked Questions about pdf-reading

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

FAQPage Schema
How do I extract text and tables from a PDF file for analysis?

To extract text and tables from a PDF, this Skill runs a content inventory then applies layout-aware extraction tools like pdfplumber and pdftotext, yielding structured text and tabular data ready for downstream analysis.

What is the best way to read scanned PDF documents that fail standard text extraction?

For scanned PDFs where standard text extraction fails, the Skill uses visual inspection via page rasterization with pdftoppm and OCR fallback, converting pages to images to recognize and extract the visual content accurately.

Can I extract embedded images and attachments from a local PDF file?

Yes, you can extract embedded images and attachments from a local PDF by utilizing pdfimages to pull raster visuals and pdfdetach to retrieve embedded files, allowing you to access and save internal document assets.

Does this PDF extraction approach work with slide-decks and data-heavy documents?

Yes, this approach works with slide-decks and data-heavy documents by combining layout-aware text extraction with page rasterization, ensuring visual layouts and complex tables are accurately captured and analyzed.

How do I read interactive form fields in a PDF?

You can read interactive form fields in a PDF by using the pypdf tool, which reads and extracts the values populated within interactive form fields for downstream data processing and analysis.

Why does my PDF text extraction return garbled characters or fail entirely?

PDF text extraction returns garbled characters due to font encoding issues or scanned content, which document diagnostics can identify before routing the file to page rasterization or OCR fallback for accurate visual extraction.