This is a systematic literature review engine that disambiguates your query before searching, then pulls from PubMed, EuropePMC, bioRxiv, and citation networks to build structured reports with evidence grading. It handles biological targets, drugs, diseases, and general academic topics, running collision-aware searches when terms have naming conflicts. Every claim gets a T1-T4 evidence tier (mechanistic down to mention-only), and it delegates to specialized skills for deep entity profiling. The workflow is rigid: clarify, disambiguate, search, synthesize into a formal report with mandatory sections and full source attribution. It's overkill for quick lookups but solid when you need a defensible lit review with proper methodology baked in.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-literature-deep-research