What problem does it solve? Finding and reading academic papers typically requires manual browsing of arXiv or PMC websites and loading entire papers into context, which wastes tokens and time. This Skill provides CLI commands to search papers with hybrid search and read only the sections you need. ## Core Features & Use Cases - Hybrid Paper Search: Search over 2M+ arXiv papers using BM25 plus vector search with filters for categories, dates, and citation counts. - Token-Efficient Reading: Retrieve papers at multiple depths, from a brief TLDR summary to specific sections or full text, so you only pay for the tokens you need. - Biomedical Literature Access: Fetch metadata and full text from PubMed Central (PMC) papers. - AI Agent Analysis: Run multi-turn reasoning queries over papers using the built-in agent with configurable LLM providers. - Use Case: During a literature review on agent memory, run a search to find the top five papers, get brief summaries of each, then read only the Methods and Results sections of the two most relevant ones. ## Quick Start Ask the assistant to search for papers on a topic, for example: use deepxiv to search for recent papers on agent memory and give me a brief summary of the top result.