This is a research literature tool that routes between quick paper lookups and multi-round search sessions. The interesting bit is the rubric system: you define 2-4 weighted criteria upfront, then the agent triages each paper against them with quoted evidence from abstracts. No LLM judge. Search happens in probe-then-refine rounds, with queries split by angle tags to avoid retreading the same ground. Works with Semantic Scholar and arXiv via DeepXiv, though you'll need API keys for full functionality. The five red lines are worth reading, especially the quote-or-zero rule for criterion scoring. Built for researchers who want structured decision trails instead of vibes-based paper lists. Pairs with separate skills for surveys and idea generation rather than trying to do everything.
npx skills add https://github.com/evoscientist/evoskills --skill paper-navigator