academic-search

Aggregate academic paper metadata from multiple sources into a unified JSON/Markdown schema.

21|6|Updated Aug 26, 2025
One-click install
npx skills add https://github.com/hepai-lab/drsai --skill academic-search-hepai-lab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: academic-search
Source: https://github.com/hepai-lab/drsai/tree/main/agent_skills/skills/academic-search
Command: npx skills add https://github.com/hepai-lab/drsai --skill academic-search-hepai-lab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill aggregates and normalizes academic paper metadata from multiple sources into a unified schema, enabling reliable deduplication, BibTeX export, and cross-platform analysis.

Core Features & Use Cases

  • API-first data retrieval across platforms with structured outputs
  • Multi-platform coverage including arXiv, Semantic Scholar, PubMed, Papers with Code, CNKI, ACM/IEEE; with browser automation fallback when APIs are unavailable
  • Built-in deduplication, BibTeX assembly, and cross-source comparison to accelerate literature reviews

Quick Start

Search for recent NeurIPS papers on time series agents and return a structured metadata list.

Frequently Asked Questions about academic-search

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

FAQPage Schema
How do I aggregate academic paper metadata from multiple platforms into a unified schema?

Aggregating academic paper metadata normalizes records from arXiv, PubMed, and Semantic Scholar into a consistent JSON schema. This Skill applies an API-first strategy to standardize outputs for deduplication and cross-source comparison.

Can I export BibTeX from search results across arXiv, PubMed, and Semantic Scholar?

Yes, BibTeX export is supported from cross-platform search results. The Skill assembles BibTeX entries from the normalized metadata schema after aggregating papers from multiple academic sources.

Does browser automation work for scraping Google Scholar and CNKI when APIs are unavailable?

Browser automation works for Google Scholar and CNKI when APIs are unavailable. The Skill applies an API-first strategy but falls back to browser automation to retrieve metadata and maintain multi-platform coverage.

What's the best way to deduplicate cross-source academic search results?

Deduplicating cross-source academic search results is best handled by normalizing metadata into a unified schema. The Skill produces consistent JSON formats that enable reliable deduplication across platforms like arXiv, PubMed, and ACM.

Do I need API keys to search Papers with Code and ACM or IEEE metadata?

API access is needed for an API-first retrieval strategy across Papers with Code, ACM, and IEEE. When APIs are unavailable, the Skill falls back to browser automation to gather academic metadata.