Research Lookup

Search Strategy Selection

Choose the right search approach based on your query type:

Routing Logic

Query arrives
    |
    +-- Contains academic keywords? (papers, DOI, journal, peer-reviewed, etc.)
    |       YES --> Academic search (Google Scholar, Semantic Scholar, arXiv, PubMed)
    |
    +-- Everything else (general research, market data, technical info, analysis)
            --> General web search

Academic Keywords (Use Academic Search)

Queries containing these terms benefit from academic-focused search engines:

• Paper finding: find papers, find articles, research papers on, published studies
• Citations: cite, citation, doi, pubmed, pmid
• Academic sources: peer-reviewed, journal article, scholarly, arxiv, preprint
• Review types: systematic review, meta-analysis, literature search
• Paper quality: foundational papers, seminal papers, landmark papers, highly cited

General Research (Use Web Search)

All other queries benefit from general web search, including:

• General research questions
• Market and industry analysis
• Technical information and documentation
• Current events and recent developments
• Comparative analysis
• Statistical data retrieval
• Complex analytical queries

Core Capabilities

1. General Research Queries

Use general web search tools for comprehensive, multi-source research.

Query Examples:
- "Recent advances in CRISPR gene editing 2025"
- "Compare mRNA vaccines vs traditional vaccines for cancer treatment"
- "AI adoption in healthcare industry statistics"
- "Global renewable energy market trends and projections"
- "Explain the mechanism underlying gut microbiome and depression"

What to look for in results:

• Comprehensive coverage from authoritative sources
• Inline citations and source URLs for verification
• Multiple perspectives and data points
• Recent publication dates

2. Academic Paper Search

Use academic search engines for scholarly, peer-reviewed sources.

Recommended Academic Search Engines:

Query Examples:
- "Find papers on transformer attention mechanisms in NeurIPS 2024"
- "Foundational papers on quantum error correction"
- "Systematic review of immunotherapy in non-small cell lung cancer"
- "Cite the original BERT paper and its most influential follow-ups"
- "Published studies on CRISPR off-target effects in clinical trials"

What to look for in results:

• Author names, titles, journals/venues, years, DOIs
• Citation counts and venue tier
• Key statistics and methodology highlights
• Research gaps and future directions

3. Technical and Methodological Information

Query Examples:
- "Western blot protocol for protein detection"
- "Statistical power analysis for clinical trials"
- "Machine learning model evaluation metrics comparison"

4. Statistical and Market Data

Query Examples:
- "Prevalence of diabetes in US population 2025"
- "Global AI market size and growth projections"
- "COVID-19 vaccination rates by country"

Paper Quality and Popularity Prioritization

CRITICAL: When searching for papers, ALWAYS prioritize high-quality, influential papers.

Citation-Based Ranking

Venue Quality Tiers

Tier 1 - Premier Venues (Always prefer):

• General Science: Nature, Science, Cell, PNAS
• Medicine: NEJM, Lancet, JAMA, BMJ
• Field-Specific: Nature Medicine, Nature Biotechnology, Nature Methods
• Top CS/AI: NeurIPS, ICML, ICLR, ACL, CVPR

Tier 2 - High-Impact Specialized (Strong preference):

• Journals with Impact Factor > 10
• Top conferences in subfields (EMNLP, NAACL, ECCV, MICCAI)

Tier 3 - Respected Specialized (Include when relevant):

• Journals with Impact Factor 5-10

Saving and Organizing Research Results

MANDATORY: Save All Results to Sources Folder

Every research-lookup result MUST be saved to the project's sources/ folder.

Research results are valuable and critical for reproducibility. Always save them.

Saving Rules

What to Save

Each saved file should include:

• The original query
• The full response text
• All citations with source URLs and DOIs where available
• Author names, titles, venues, and years for academic papers
• A timestamp of when the search was performed

Why Save Everything

1. Reproducibility: Every citation and claim can be traced back to its raw research source
2. Context Window Recovery: If context is compacted, saved results can be re-read without re-querying
3. Audit Trail: The sources/ folder documents exactly how all research information was gathered
4. Reuse Across Sections: Multiple sections can reference the same saved research without duplicate queries
5. Cost Efficiency: Check sources/ for existing results before making new searches
6. Peer Review Support: Reviewers can verify the research backing every citation

Before Making a New Query, Check Sources First

Before running a new search, check if a relevant result already exists:

ls sources/  # Check existing saved results

If a prior lookup covers the same topic, re-read the saved file instead of making a new search.

Integration with Scientific Writing

This skill enhances scientific writing by providing:

1. Literature Review Support: Gather current research for introduction and discussion — save to sources/
2. Methods Validation: Verify protocols against current standards — save to sources/
3. Results Contextualization: Compare findings with recent similar studies — save to sources/
4. Discussion Enhancement: Support arguments with latest evidence — save to sources/
5. Citation Management: Provide properly formatted citations — save to sources/

Complementary Tools

Search Tips for Better Results

General Web Search Tips

• Use specific, targeted queries rather than broad ones
• Include year constraints for recent results (e.g., "2024-2025")
• Use domain-specific terminology for more precise results
• Combine multiple search queries to triangulate information

Academic Search Tips

• Use author names and venue names to narrow results
• Search by DOI for exact paper retrieval
• Use citation graphs (Semantic Scholar, Connected Papers) to find related work
• Check "cited by" lists to find follow-up work
• Use Boolean operators: AND, OR, NOT for complex queries
• Filter by year range, venue, and citation count when available

Evaluating Search Results

• Cross-reference claims across multiple sources
• Prefer primary sources over secondary reporting
• Check publication dates for recency
• Verify author credentials and institutional affiliations
• Look for peer review status (published vs. preprint)

Error Handling and Limitations

Known Limitations:

• Web search results may not include the most recent publications (indexing delay)
• Academic search engines may not access full text behind paywalls
• Search tools cannot access proprietary or restricted databases
• Citation counts may vary across different databases

Best Practices:

• If initial results are insufficient, rephrase the query with different terminology
• Use multiple search engines to ensure comprehensive coverage
• For paywalled papers, check if preprint versions exist on arXiv or institutional repositories
• Always verify critical claims against primary sources

Usage Examples

Example 1: General Research

Query: "Recent advances in transformer attention mechanisms 2025"

Approach: Use general web search. Look for blog posts, survey articles, and news coverage of recent papers.

Expected Output: Summary of key innovations, performance benchmarks, and links to relevant papers and articles.

Example 2: Academic Paper Search

Query: "Find papers on CRISPR off-target effects in clinical trials"

Approach: Use PubMed and Google Scholar. Filter for peer-reviewed articles from the last 3 years.

Expected Output: Curated list of 5-8 high-impact papers with full citations, DOIs, citation counts, and venue information.

Example 3: Comparative Analysis

Query: "Compare and contrast mRNA vaccines vs traditional vaccines for cancer treatment"

Approach: Use general web search for recent review articles and clinical trial summaries.

Expected Output: Structured comparison with data from multiple sources and cited evidence.

Example 4: Market Data

Query: "Global AI adoption in healthcare statistics 2025"

Approach: Use general web search targeting industry reports, government statistics, and market research firms.

Expected Output: Current market data, adoption rates, growth projections, and regional analysis with source citations.

Summary

This skill serves as a guide for research information lookup:

• General web search: Comprehensive, multi-source research for any topic
• Academic search engines: Paper-specific searches via Google Scholar, Semantic Scholar, arXiv, PubMed, and DBLP
• Smart routing: Choose the right search approach based on query type
• Result preservation: Always save research results to sources/ for reproducibility and reuse
• Quality focus: Prioritize high-impact venues and well-cited papers