Semanticscholar Skill

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.

skills.sh installs: 3.5K
GitHub stars: 100
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agents365-ai/365-skills --skill semanticscholar-skill --agent claude-code

Installs into .claude/skills of the current project.

Files

Semantic Scholar Search Workflow

Search academic papers via the Semantic Scholar API using a structured 4-phase workflow.

Critical rule: NEVER make multiple sequential Bash calls for API requests. Always write ONE Python script that runs all searches, then execute it once. All rate limiting is handled inside s2.py automatically.

Phase 1: Understand & Plan

Parse the user's intent and choose a search strategy:

Decision Tree

Default to search_bulk(). Per Semantic Scholar's own docs, bulk search is preferred over relevance search for most cases because relevance search is more resource-intensive. Use search_relevance() only when you need TLDR fields or author/citation details inline.

SKILL.md on GitHub