Semantic Scholar Search
Structured 4-phase Semantic Scholar search with a Python helper that handles rate limits and boolean queries.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 7412e88
Live-tested against the real API: a naive direct call (no skill) hit a 429 immediately, while the skill's s2.py script (built-in backoff, snake_case-to-camelCase filter translation) returned 10 real, correctly-filtered RAG-for-code papers with citation counts on the first try.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Semantic Scholar Search does
Searches academic papers, citations, and authors via the Semantic Scholar API through a 4-phase plan-execute-present-followup workflow, defaulting to bulk boolean search per Semantic Scholar's own guidance. Ships a Python helper (s2.py) with automatic rate-limiting and exponential backoff for both keyed and anonymous use, plus formatters for tables, citation intent, and BibTeX export. Use for literature search, citation analysis, author lookup, or paper-recommendation requests.
How to install Semantic Scholar Search
git clone https://github.com/Agents365-ai/semanticscholar-skill
cd semanticscholar-skill
mkdir -p ~/.claude/skills
cp -r skills/semanticscholar-skill ~/.claude/skills/semanticscholar-skill
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Semantic Scholar Search
-
/semanticscholar-skillStructured 4-phase Semantic Scholar search with a Python helper that handles rate limits and boolean queries.
It also activates on plain-language prompts like these:
-
Search Semantic Scholar for papers on transformer attention -
Find citation counts and authors for this paper on arXiv -
Do a literature review on graph neural networks for me
Frequently asked questions
- Is the Semantic Scholar Search skill free?
- Yes. The skill itself is free from Agents365-ai/semanticscholar-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Semantic Scholar Search work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Live-tested against the real API: a naive direct call (no skill) hit a 429 immediately, while the skill's s2.py script (built-in backoff, snake_case-to-camelCase filter translation) returned 10 real, correctly-filtered RAG-for-code papers with citation counts on the first try.
- What is the Semantic Scholar Search SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Semantic Scholar Search?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Semantic Scholar Search with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.