search-pdf

Extract text from PDFs and search for keywords with page numbers and context.

Updated Mar 28, 2026

Search Tags:#pdf #research #information retrieval #text extraction #keyword search

Ready to run

npx skills add https://github.com/bgpopescu/popescu_claude --skill search-pdf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: search-pdf
Source: https://github.com/bgpopescu/popescu_claude/tree/main/.claude/skills/search-pdf
Command: npx skills add https://github.com/bgpopescu/popescu_claude --skill search-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fitz, pymupdf, pip, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Finding specific information in large PDFs can be time-consuming. This Skill streamlines the process by extracting text, searching for keywords, and providing relevant page numbers and context.

Core Features & Use Cases

PDF Text Extraction: Extracts text from PDFs for further processing.
Keyword Search: Searches for specific information within the PDF.
Contextual Results: Provides page numbers and context around the found information.
Use Case: If you're looking for a specific table or figure in a 600-page book, this Skill can quickly locate it and provide the necessary context.

Quick Start

Run the 'search-pdf' skill with the path to your PDF and the search query, e.g., /search-pdf books/acemoglu_why_nations_fail.pdf "extractive institutions in Congo"

Frequently Asked Questions about search-pdf

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

FAQPage Schema

How do I search for specific keywords in a PDF document?▼

To extract text from a PDF for research, you can use Python libraries like PyMuPDF or fitz to parse the document. This Skill leverages these dependencies to instantly turn PDFs into editable text for literature review and information retrieval.

What is the best way to find a specific table in a large PDF file?▼

Yes, you can locate specific information within large PDFs by running this Skill with your file path and search query. It handles literature review tasks by extracting text and pinpointing the exact page numbers where your keywords appear.

Does this keyword search approach provide page numbers and context?▼

To start searching PDF text, run the skill command with your file path and search query, such as `/search-pdf document.pdf "search term"`. It immediately parses the PDF and returns matching keywords with their page numbers and context.

Do I need Python libraries installed to extract text from PDFs?▼

Python libraries like pymupdf and fitz are highly effective for PDF text extraction and keyword search. This Skill uses these specific dependencies to parse PDF files and return contextual results with page numbers for research purposes.

Can I use this for literature review in large research documents?▼

This PDF text extraction approach is optimized for searching specific information rather than converting entire documents at once. It provides targeted contextual results and page numbers, making it ideal for locating specific data rather than bulk conversion.