literature-search

Search OpenAlex, Semantic Scholar, and arXiv, then deduplicate results into a structured dataset.

33|6|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill literature-search-xjtulyc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: literature-search
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/00-universal/literature-search
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill literature-search-xjtulyc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pandas, matplotlib, pyalex, semanticscholar.

What problem does it solve?

This Skill solves the problem of missing relevant research and wasting time when searching for academic papers across multiple sources with inconsistent coverage and formats.

Core Features & Use Cases

  • Cross-database literature search: Query OpenAlex, Semantic Scholar, and arXiv in a unified workflow.
  • Deduplication & organization: Remove duplicates using DOI matching and normalized title comparison, then standardize results into a single table.
  • Research discovery enhancements: Perform citation snowballing to find papers citing a seed DOI and visualize annual publication trends to gauge momentum.
  • Export for downstream use: Export deduplicated results to BibTeX for Zotero/LaTeX workflows and produce CSV outputs for analysis.
  • Use case: You are preparing a systematic review on a topic and need a consolidated, deduplicated set of papers plus a BibTeX file and a quick view of how output has changed over time.

Quick Start

Use the literature-search skill to search for recent work on "LLM hallucination factual accuracy" and export a deduplicated BibTeX file.

Frequently Asked Questions about literature-search

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

FAQPage Schema
How do I search for academic papers across multiple databases and remove duplicates?

Cross-database academic literature search queries OpenAlex, Semantic Scholar, and arXiv simultaneously, then deduplicates results by matching DOIs and normalizing titles into a single structured dataset.

What is citation snowballing and how does it work with a seed DOI?

Citation snowballing finds papers citing a seed DOI. You provide a starting DOI, and the search queries OpenAlex and Semantic Scholar to retrieve and consolidate all forward-citing publications into your dataset.

Can I export cross-database literature search results to BibTeX for Zotero or LaTeX?

Yes, you can export deduplicated literature search results to BibTeX for Zotero or LaTeX workflows. The skill standardizes records from OpenAlex, Semantic Scholar, and arXiv, and also supports CSV outputs for analysis.

Does this literature search tool respect API rate limits for OpenAlex and Semantic Scholar?

Yes, the literature search respects documented API rate limits and pagination behavior for OpenAlex and Semantic Scholar to ensure stable cross-database querying without exceeding request thresholds.

How do I monitor weekly arXiv preprints within a specific time window?

To monitor weekly arXiv preprints, apply the literature search workflow to arXiv within a specified time window, retrieving recent preprints and consolidating them into a structured dataset for tracking latest research.

What's the best way to visualize annual publication trends for a research topic?

The best way to visualize annual publication trends is to aggregate deduplicated search results by year and generate trend visualizations, allowing you to gauge research momentum and output changes over time.