A solid wrapper around the Semantic Scholar API with a structured four-phase workflow that keeps you from shooting yourself in the foot with rate limits. The skill pushes you to write a single Python script instead of hammering the API with sequential bash calls, and it auto-handles retries and backoff. Works unauthenticated but you'll want an API key for serious use. The decision tree is genuinely helpful: it steers you toward bulk search by default and only uses relevance search when you need TLDRs or inline author details. Includes citation traversal, multi-seed recommendations, and BibTeX export. The worked examples show real patterns like filtering an author's papers locally or sorting citations by impact.
npx skills add https://github.com/agents365-ai/365-skills --skill semanticscholar-skill