Skills gene-database
🧬

gene-database

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

Query NCBI Gene Database

Also available from: davila7

Access comprehensive gene data from NCBI including sequences, annotations, and functional information. Search by gene symbol, ID, or biological context to retrieve RefSeqs, Gene Ontology, chromosomal locations, and phenotypes for bioinformatics research.

Supports: Claude Codex Code(CC)
🥉 73 Bronze
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 "gene-database". Find information about BRCA1 in human

Expected outcome:

  • Gene ID: 672
  • Symbol: BRCA1
  • Description: BRCA1 DNA repair associated
  • Organism: Homo sapiens
  • Chromosome: 17
  • Location: 17q21.31

Using "gene-database". Find genes associated with diabetes in human

Expected outcome:

  • Gene ID list with symbol, description, and chromosome for diabetes-associated genes
  • Search query: diabetes[disease] AND human[organism]

Using "gene-database". Get batch gene data for TP53, EGFR, KRAS

Expected outcome:

  • Batch results with gene ID, symbol, description, organism, chromosome, and map location for each gene

Security Audit

Low Risk
v4 • 1/17/2026

This is a legitimate bioinformatics tool for querying NCBI Gene database. All 374 static findings are false positives: markdown backticks in documentation are code formatting (not shell execution), API keys are user-provided CLI arguments (not hardcoded secrets), hardcoded URLs are official NCBI API endpoints, and the network+credential+file pattern is standard API client behavior. No data exfiltration or malicious patterns detected.

8
Files scanned
2,293
Lines analyzed
4
findings
4
Total audits

Risk Factors

🌐 Network access (4)
scripts/query_gene.py:19 scripts/fetch_gene_data.py:17 scripts/batch_gene_lookup.py:53 references/api_reference.md:20-22
⚙️ External commands (3)
SKILL.md:34-175 references/api_reference.md:20-356 references/common_workflows.md:26-398
🔑 Env variables (3)
scripts/query_gene.py:23-43 scripts/fetch_gene_data.py:56-71 scripts/batch_gene_lookup.py:41-48
📁 Filesystem access (1)
scripts/batch_gene_lookup.py:287
Audited by: claude View Audit History →

Quality Score

64
Architecture
100
Maintainability
87
Content
21
Community
90
Security
83
Spec Compliance

What You Can Build

Gene annotation workflows

Retrieve comprehensive gene data including sequences, GO terms, and phenotypes for functional analysis.

Batch gene data collection

Process gene lists efficiently with rate limiting for large-scale genomic studies.

Gene information lookup

Query gene symbols and retrieve detailed information for educational purposes.

Try These Prompts

Find a gene symbol 
Find information about the {gene_symbol} gene in {organism} including its chromosomal location and function.
Get sequence data 
Retrieve RefSeq accession numbers and gene sequence data for {gene_id} in JSON format.
Batch gene lookup 
Look up gene information for the following genes from {organism}: {gene_list}. Return the results as JSON.
Gene function search 
Find genes associated with {biological_process} in {organism} using Gene Ontology terms.

Best Practices

  • Include the organism in your query to avoid ambiguous results from gene symbols that exist in multiple species
  • Use Gene IDs instead of symbols when precision is required, as gene symbols can change over time
  • Include your NCBI API key for faster batch processing (up to 10 requests per second)

Avoid

  • Do not make individual requests in a loop without rate limiting, as this will trigger NCBI rate limits
  • Do not rely solely on gene symbols for permanent storage, as official nomenclature can change
  • Do not assume all gene symbols are unique within an organism without verifying

Frequently Asked Questions

How do I get an NCBI API key?
Register for a free API key at https://www.ncbi.nlm.nih.gov/account to increase rate limits from 3 to 10 requests per second.
What gene formats are supported?
You can search by official gene symbol (BRCA1), Gene ID (672), or use complex queries with GO terms and disease keywords.
Can I retrieve protein sequences?
Yes, the skill retrieves RefSeq accessions for transcripts and proteins associated with the gene.
How many genes can I query at once?
The batch script supports hundreds of genes with automatic rate limiting. ESummary accepts up to 500 IDs per request.
What output formats are available?
Data can be returned as JSON for programmatic use, XML for detailed metadata, or human-readable text summaries.
Does this skill store any data?
No, this skill only queries NCBI APIs in real-time. All data is returned directly to the user or written to a user-specified output file.

Developer Details

Author

K-Dense-AI

License

MIT

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/gene-database

Ref

main

File structure

📁 references/

📄 api_reference.md

📄 common_workflows.md

📁 scripts/

📄 batch_gene_lookup.py

📄 fetch_gene_data.py

📄 query_gene.py

📄 evaluation.json

📄 SKILL.md