Paper Navigator

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.

skills.sh installs: 367
GitHub stars: 488
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add evoscientist/evoskills --skill paper-navigator --agent claude-code

Installs into .claude/skills of the current project.

Files

Paper Navigator

Find and read academic papers. Route by intent, judge by relevance.

        User
         │
         ▼
   ┌── Router ──┐
   │            │
   ▼            ▼
 POINT      LIST/ITERATIVE
(1 paper)   (Probe + up to 3 paper rounds:
             R2 breadth / R3 deepen / R4 close)

The agent does relevance judgment — no LLM-as-judge is called, no numeric scoring. You author the rubric, you triage each paper, you rank by relevance.

Setup

Script paths in this document are relative to this skill's directory. Resolve scripts/<name>.py against that directory, but keep the execution working directory at the task workspace; do not cd into the installed skill directory.

Dependencies: pip install deepxiv-sdk httpx (also listed in requirements.txt at the skill root). Install into the environment the user is working in.

arXiv access (arxiv_monitor, scholar_search fallback) uses the DeepXiv SDK: pip install deepxiv-sdk, then deepxiv token once to provision a free API token (saved to ~/.env). The skill reads the token from DEEPXIV_API_TOKEN/DEEPXIV_TOKEN in the environment, or from ./.env / ~/.env.