Skills research-lookup
🔬

research-lookup

Low Risk 🔑 Env variables🌐 Network access📁 Filesystem access⚙️ External commands

Search Academic Literature and Research Papers

Also available from: davila7

Finding current academic research requires searching multiple databases and evaluating source quality. This tool searches scholarly literature through Perplexity Sonar models with automatic model selection based on query complexity and citation-focused results.

Supports: Claude Codex Code(CC)
⚠️ 68 Poor
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Test it

Using "research-lookup". Recent advances in mRNA vaccine technology 2024

Expected outcome:

  • Key Findings: Summary of 5 major research advances from 2024
  • Top Paper: Smith et al. 2024, Nature Medicine (cited 200+ times)
  • Venue: Nature Medicine (Tier 1)
  • DOI: https://doi.org/10.xxxx/xxxx
  • 4 additional high-impact citations included

Using "research-lookup". Compare transformer versus RNN for sequence modeling

Expected outcome:

  • Transformer models show superior parallelization and long-range dependency handling
  • RNNs offer lower computational overhead for short sequences
  • Key Study: Vaswani et al. 2017 (Attention Is All You Need) - 50,000+ citations
  • Performance benchmarks across multiple NLP tasks included

Using "research-lookup". Western blot protocol for protein detection

Expected outcome:

  • Step-by-step protocol from recent Nature Methods review
  • Required reagents and equipment listed
  • Common pitfalls and troubleshooting tips provided
  • Reference to seminal antibody validation paper

Security Audit

Low Risk
v4 • 1/17/2026

This is a legitimate academic research tool that makes API calls to OpenRouter for literature searches. All 146 static findings are false positives: (1) API key environment reads are standard authentication for OPENROUTER_API_KEY, (2) network calls target the legitimate OpenRouter API endpoint, (3) 'external commands' flagged in SKILL.md are documentation examples showing command syntax, not runtime code execution, and (4) 'weak cryptographic algorithm' mentions are ML architecture names (transformer, RNN) misidentified as cryptographic algorithms. No malicious patterns detected after intent analysis.

6
Files scanned
2,314
Lines analyzed
4
findings
4
Total audits
Audited by: claude View Audit History →

Quality Score

45
Architecture
100
Maintainability
85
Content
24
Community
90
Security
78
Spec Compliance

What You Can Build

Literature Review Assistant

Gather current research for manuscripts and stay current with recent developments in your field.

Academic Source Finder

Find credible academic sources for essays and papers with proper citations.

Technical Documentation Lookup

Look up specifications, protocols, and methodologies for technical documentation.

Try These Prompts

Basic Search
Research the latest advances in [TOPIC] from 2024. List key papers with citations.
Comparative Analysis
Compare [METHOD_A] versus [METHOD_B] for [APPLICATION]. Include pros, cons, and relevant studies.
Deep Analysis
Explain the mechanism of [PHENOMENON] and identify key papers that established this understanding.
Citation Finding
Find the most influential foundational papers on [TOPIC] that every researcher should know.

Best Practices

  • Use specific query terms including timeframe and research type for best results
  • Use reasoning keywords like compare, analyze, or explain for complex queries
  • Verify all citations against primary sources before including in manuscripts
  • Break complex research questions into multiple focused queries

Avoid

  • Do not use vague queries like tell me about AI - be specific about topic and scope
  • Do not rely solely on AI-generated summaries - always verify with primary sources
  • Do not use for circumventing paywalls or accessing restricted content
  • Do not present AI-generated content as original research without proper attribution

Frequently Asked Questions

What models does this skill use?
It uses Perplexity Sonar Pro Search for fast lookups and Sonar Reasoning Pro for complex analytical queries.
How does automatic model selection work?
Queries with reasoning keywords like compare, analyze, or explain trigger the deep reasoning model automatically.
What API key do I need?
Set the OPENROUTER_API_KEY environment variable with your OpenRouter API credentials.
What sources does it prioritize?
Peer-reviewed journals, high-impact venues like Nature and Science, and highly-cited papers are prioritized.
Can I save research results to a file?
Use the --output flag to save results to a file, or --json for JSON format output.
How many citations does it return?
The skill returns 5-10 high-quality citations with full bibliographic information and DOI links when available.