semantic-scholar-deep

Name: semantic-scholar-deep
Availability: InStock
Author: CodeAlive

Orchestrate Semantic Scholar discovery, batching, and citation graph traversal.

Updated Mar 29, 2026

Search Tags:#research #citations #multi-step #references #graph #literature-review #semantic-scholar

Ready to run

npx skills add https://github.com/CodeAlive-AI/awesome-agent-skills --skill semantic-scholar-deep

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: semantic-scholar-deep
Source: https://github.com/CodeAlive-AI/awesome-agent-skills/tree/main/skills/semantic-scholar-deep
Command: npx skills add https://github.com/CodeAlive-AI/awesome-agent-skills --skill semantic-scholar-deep

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Semantic Scholar often lacks in-depth backward references, forward citations, batch lookups, and multi-hop citation graphs. This Skill orchestrates Exa MCP discovery, fast S2 metadata retrieval, and a token-isolated deep-research workflow to fill those gaps and produce compact reports.

Core Features & Use Cases

Inline usage: fetch references, recommendations, or batch lookups for a seed paper, or snippet search across the corpus.
Delegated deep research: use the bundled deep-paper-researcher subagent to run literature reviews, seed-expansion, and citation-graph analyses without cluttering the main context.
Output hygiene: produce concise, ranked reports (not raw API dumps) and optional graph artifacts.

Quick Start

Run the inline commands to fetch references or recommendations for a paper, or delegate multi-step literature reviews to the deep-paper-researcher for a structured report.

Frequently Asked Questions about semantic-scholar-deep

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a citation graph around a seed paper for a literature review?▼

To build a citation graph for a literature review, the skill orchestrates Semantic Scholar discovery and multi-hop graph traversal. It batches metadata retrieval and applies Python scripts to map forward citations and backward references around your seed paper, producing a concise ranked report.

Can I run a state-of-the-art survey and novelty check using Semantic Scholar?▼

Yes, you can run a state-of-the-art survey and novelty check using Semantic Scholar. The skill delegates multi-step literature reviews to a bundled subagent, isolating tokens to traverse citation graphs and snippet search the corpus without cluttering your main context.

What is the best way to fetch batch lookups and multi-hop references from Semantic Scholar?▼

The best way to fetch batch lookups and multi-hop references is using the bundled Python scripts. The skill utilizes ss_client.py for fast metadata retrieval and citation_graph.py to orchestrate batching and graph traversal, returning compact reports instead of raw API data.

Does this Semantic Scholar deep research workflow require any external dependencies?▼

This Semantic Scholar deep research workflow requires no external dependencies but needs access to the bundled Python scripts. It orchestrates Exa MCP discovery and the semantic-scholar-lookup integration internally to fill in-depth reference gaps.

Why does Semantic Scholar lack in-depth forward citations and backward references for my paper?▼

Semantic Scholar often lacks in-depth forward citations and backward references due to standard API limits. This skill fills those gaps by orchestrating Exa MCP discovery with multi-hop citation graph traversal and batch lookups to generate comprehensive reference data.