pdf-extract

Extract text from PDF files using the pdftotext command-line utility.

39|1|Updated Jul 2, 2026
One-click install
npx skills add https://github.com/HKU-MMLab/UniClawBench --skill pdf-extract-hku-mmlab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-extract
Source: https://github.com/HKU-MMLab/UniClawBench/tree/main/injection/101_skill_usage/task_101_33_exhibitor_compare/skills/pdf-extract
Command: npx skills add https://github.com/HKU-MMLab/UniClawBench --skill pdf-extract-hku-mmlab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? PDF files store content in a binary format that language models cannot read directly. This Skill converts PDF documents into plain text so their content can be processed, summarized, or analyzed by an LLM. ## Core Features & Use Cases - Full-Document Extraction: Convert an entire PDF into plain text with a single command. - Page-Range Extraction: Extract text from specific pages (e.g., pages 1-5) to focus on relevant sections of large documents. - Use Case: When a task provides a PDF report or exhibitor catalog, extract its text first so you can search, compare, and reason over the document content. ## Quick Start Extract all text from the PDF file 'document.pdf' so I can review its contents.

Frequently Asked Questions about pdf-extract

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

FAQPage Schema
How do I extract text from a PDF file?▼

Run pdf-extract followed by the PDF filename, for example pdf-extract "document.pdf". This uses pdftotext from poppler-utils to convert the entire document into plain text for further processing.

How to extract text from specific PDF pages only?▼

Pass the --pages flag with a page range, such as pdf-extract "document.pdf" --pages 1-5. This limits extraction to the specified pages, which is useful for large documents where only a section is relevant.

What tool does this PDF extraction use?▼

It uses pdftotext, a command-line utility from the poppler-utils package. The task workspace provides pdftotext during setup, so no manual installation is required during the task.

What should I do if pdftotext is not available?▼

Report the missing pdftotext command as an environment problem. The Skill explicitly instructs not to install packages during the user task, since the workspace is expected to provide the binary during setup.

Can pdftotext extract text from scanned PDFs?▼

pdftotext extracts embedded text layers only and cannot perform OCR on scanned image-based pages. Documents without a text layer will produce little or no output.