Unified CLI/Python interface to 20+ genomic databases. Gene lookups (Ensembl search/info/seq), BLAST/BLAT, AlphaFold, Enrichr enrichment, OpenTargets disease/drug, CELLxGENE single-cell, cBioPortal/COSMIC cancer, ARCHS4 expression. Spans genomics, proteomics, disease. For batch/advanced BLAST use biopython; for multi-DB Python SDK use bioservices.
SkillScore96Maintained
Automatic
◆Research pack
Last verified 8/24/2026
What it changes
Passed 22 of 23 test cases with the skill, and 15 of 23 without it.
Without skill65%
With skill96%
Checks it passed that the model alone missed
Uses database='transcription'
Calls gget.ref with which='cdna'
Sets release=112 in the gget.ref call
and 5 more in the full report
7 fixed15 passed either way1 still failing0 broke
Pass-rate lift
+30 pp
Tokens
+328%
Agent turns
0%
Response time
-32%
Model gemini-3.6-flashMeasured 8/24/2026v122 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
Which built-in gget Enrichr shortcut string maps to the ChEA transcription factor target database?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses database='transcription'
Missed
Passed
case-15 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md542 lines3 files
gget — Unified Genomic Database Access
Overview
gget is a command-line and Python package providing unified access to 20+ genomic databases and analysis methods. Query gene information, sequences, protein structures, expression data, and disease associations through a consistent interface. All modules work as both CLI tools and Python functions, returning DataFrames (Python) or JSON/CSV (CLI).
When to Use
Looking up gene information (names, IDs, descriptions) across species from Ensembl
Retrieving nucleotide or protein sequences for Ensembl gene/transcript IDs
Running BLAST or BLAT searches against standard reference databases
Predicting protein 3D structures with AlphaFold2 from amino acid sequences
Performing gene set enrichment analysis (GO, KEGG, disease terms) via Enrichr
Querying single-cell RNA-seq datasets from CELLxGENE Census
Finding disease and drug associations for a gene target via OpenTargets
Downloading Ensembl reference genomes and annotations for a species
Finding cancer mutations and genomic alterations via cBioPortal or COSMIC
Getting tissue expression and correlated genes from ARCHS4
For batch processing or advanced BLAST parameters, use biopython instead
For programmatic multi-database workflows with rate limiting, use bioservices instead
Prerequisites
Python packages: gget
Optional setup: Some modules require gget setup <module> before first use (alphafold, cellxgene, elm, gpt)
Environment: Clean virtual environment recommended to avoid dependency conflicts
API notes: gget queries remote databases — rate-limit large batch queries with time.sleep(). Databases update biweekly; keep gget updated. Max ~1000 Ensembl IDs per gget.info() call
pip install gget
# Optional: setup modules that need additional dependencies
gget setup alphafold # ~4GB model parameters, requires OpenMM
gget setup cellxgene # cellxgene-census package
gget setup elm # local ELM database