scholarag

What problem does it solve?

Researchers face immense time and cost burdens conducting systematic literature reviews (traditionally 6-12 months, $140K+). Manually screening thousands of papers is prone to fatigue and inconsistency. This Skill automates the entire process, from paper retrieval to RAG-powered analysis, drastically reducing time and cost while enhancing rigor and reproducibility.

Core Features & Use Cases

• Automated Paper Retrieval: Fetches relevant academic papers from Semantic Scholar, OpenAlex, and arXiv, building a comprehensive dataset.
• AI-Assisted PRISMA Screening: Intelligently screens papers for relevance (with 50% or 90% confidence thresholds), ensuring PRISMA 2020 compliance and drastically reducing manual effort.
• RAG-Powered Analysis: Builds a vector database from included PDFs, enabling conversational AI queries to extract deep research insights and generate publication-ready documentation.
• Use Case: A PhD student needs to conduct a systematic review for their dissertation. Instead of spending months manually sifting through thousands of papers, they use ScholaRAG to automate the entire process in days, focusing their time on synthesizing findings and writing.

Quick Start

Initialize a new systematic review project

python scholarag_cli.py init
--name "AI-Chatbots-Language-Learning"
--question "How do AI chatbots improve speaking proficiency?"
--domain education
--project-type systematic_review