gget
gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.
Security Assessment
About gget
The gget skill provides a workflow for using the `gget` CLI and Python package to run quick bioinformatics lookups across genomic reference databases. It solves the problem of needing fast, first-pass access to gene metadata, sequences, and BLAST/BLAT-style searches without standing up a full local pipeline (Biopython, Snakemake, Nextflow, BLAST+). The skill emphasizes reproducibility, guiding users to record versions, arguments, and database assumptions before moving to heavier tooling.
The skill documents installation in a clean Python environment (venv or uv), the CLI and Python call shapes, and a set of common modules: `search` and `info` for Ensembl/UniProt IDs and metadata, `seq` for nucleotide/amino-acid sequences, `ref` for reference genome links, `blast`/`blat`/`muscle`/`diamond` for alignment, `alphafold`/`pdb` for structure references, and enrichment/target/disease modules such as `enrichr`, `opentargets`, `archs4`, `bgee`, `cbio`, and `cosmic`. It includes worked CLI and Python examples (e.g., BRCA1 lookups) and a reproducibility-log table capturing date, version, module, query, species/assembly, and output.
The target users are researchers, bioinformaticians, and students who need quick evidence-gathering against public genomic databases. It is explicitly positioned for first-pass exploratory work rather than regulated clinical interpretation, high-throughput production pipelines, or version-pinned local indexing, which the skill recommends handling with dedicated workflows instead.
FAQ
What do I need installed to use this skill?
A clean Python environment with the `gget` package installed (via pip or uv). The skill recommends creating a fresh venv, upgrading pip, and installing the latest gget, then running `gget --help` to verify.
Can I use gget for clinical or diagnostic interpretation?
No. The skill explicitly says to use a dedicated workflow instead when the task requires regulated clinical interpretation, high-throughput production pipelines, or fine-grained control over database versions and local indexes. gget output should be labeled as database output, not clinical interpretation.
How do I keep queries reproducible?
Record the gget version, module name, arguments, species/assembly, output filename and date, and any optional dependencies installed via `gget setup`. The skill provides a reproducibility-log table template for this.
Do all gget modules work with any Python version?
No. The skill warns not to assume every module supports every Python version or dependency set; some optional scientific dependencies have narrower version support than the core package, so isolated environments are recommended.
Does gget query live databases?
Yes. It queries upstream genomic reference databases (Ensembl, UniProt, and others) that change over time, so the skill advises upgrading gget and re-checking module docs before relying on an older environment.
Install gget
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
affaan-m/everything-claude-code