pdf-retrieve

Retrieve open-access PDF URLs for academic papers via Unpaywall, PubMed Central, arXiv, and Semantic Scholar.

Updated Mar 6, 2026

Search Tags:#pdf #research #download #open access #literature #doi

Ready to run

npx skills add https://github.com/ryan-ressmeyer/llm-skills --skill pdf-retrieve

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-retrieve
Source: https://github.com/ryan-ressmeyer/llm-skills/tree/main/pdf-retrieve
Command: npx skills add https://github.com/ryan-ressmeyer/llm-skills --skill pdf-retrieve

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of finding and downloading PDF versions of academic papers, ensuring you have the full text for your research without manual searching or paywall frustrations.

Core Features & Use Cases

Open-Access Prioritization: Automatically checks Unpaywall, PubMed Central, arXiv, and Semantic Scholar for free PDF versions.
Paywall Handling: Gracefully handles paywalled articles by informing the user and providing a direct DOI link, never failing silently.
Use Case: When a new paper is added to your literature database without a PDF, this Skill can find and download it, or guide you on how to obtain it manually.

Quick Start

Use the pdf-retrieve skill to find the open access PDF for the paper with DOI 10.1523/JNEUROSCI.1234-19.2019.

Frequently Asked Questions about pdf-retrieve

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

FAQPage Schema

How do I download open access PDFs for academic papers using a DOI?▼

You can download open access PDFs by querying Unpaywall, PubMed Central, arXiv, and Semantic Scholar with the paper's DOI. The tool retrieves direct PDF URLs from these repositories automatically.

What happens when a research paper is behind a paywall?▼

When a paper is paywalled, the tool provides the direct DOI link and instructions for manual retrieval instead of failing silently. It checks all open access sources before reporting the paywall.

Do I need Python libraries to retrieve literature PDFs automatically?▼

Yes, you need Python with the requests and python-dotenv libraries. These handle API interactions with academic databases and environment variable management for service credentials.

Can I find preprint PDFs from arXiv and Semantic Scholar?▼

Yes, the tool queries preprint servers like arXiv and Semantic Scholar alongside Unpaywall and PubMed Central to locate open access PDF versions of research papers.

What is the best way to automate adding PDFs to a literature database?▼

Use this tool to automatically find and retrieve open access PDFs when new papers are added to your literature database. It checks multiple academic repositories and handles paywalled articles gracefully.