agentleFS
renepfrenepf/claude-skills/scientific-pkg-gget/SKILL.md

gget

Skill0 starsChanged 4 months agoMITView on GitHub

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

  • Installs packages

14 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill when a task needs quick bioinformatics lookup across genomic reference databases with the gget CLI or Python package.

    line 10
  2. Very specific:

    Use a dedicated workflow instead of gget when the task requires regulated clinical interpretation, high-throughput production pipelines, or …

    line 24
  3. Distinctive:

    Use a clean Python environment.

    line 30
  4. Very specific:

    If uv is available:

    line 40
  5. Very specific:

    Before relying on an older environment, upgrade gget and re-check the module docs.

    line 48
  6. Distinctive:

    Check the current module documentation for arguments.

    line 71
  7. Distinctive:

    Run a small query first.

    line 72
  8. Distinctive:

    Use current upstream docs for exact arguments.

    line 78
  9. Distinctive:

    Do not assume every module supports every Python version or dependency set.

    line 94
  10. Distinctive:

    Run a small BLAST query:

    line 118

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

gget

Use this skill when a task needs quick bioinformatics lookup across genomic reference databases with the gget CLI or Python package.

When to Use

  • Finding Ensembl IDs, gene metadata, transcript details, or sequences.
  • Running quick BLAST or BLAT lookups without building a full local pipeline.
  • Fetching reference genome links and annotations from Ensembl.
  • Querying protein structure, pathway, cancer, expression, or disease-association modules through a single interface.
  • Creating a reproducible first-pass evidence log before moving to heavier tools such as Biopython, Snakemake, Nextflow, BLAST+, or database-specific clients.

Use a dedicated workflow instead of gget when the task requires regulated clinical interpretation, high-throughput production pipelines, or fine-grained control over database versions and local indexes.

Installation

Use a clean Python environment.

python -m venv .venv
. .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install --upgrade gget
gget --help

If uv is available:

uv venv
. .venv/bin/activate
uv pip install gget

Before relying on an older environment, upgrade gget and re-check the module docs. The upstream databases queried by gget change over time.

Basic Patterns

CLI shape:

gget <module> [arguments] [options]

Python shape:

import gget

result = gget.search(["BRCA1"], species="human")
print(result)

Common workflow:

  1. Identify the species, assembly, gene ID type, and database needed.
  2. Check the current module documentation for arguments.
  3. Run a small query first.
  4. Save output with an explicit filename and date.
  5. Record module name, version, arguments, and database assumptions.

Common Modules

Use current upstream docs for exact arguments. These modules are common first choices:

  • gget search: find Ensembl IDs from search terms.
  • gget info: retrieve metadata for Ensembl, UniProt, or related IDs.
  • gget seq: fetch nucleotide or amino-acid sequences.
  • gget ref: retrieve reference genome download links.
  • gget blast: run a quick BLAST query.
  • gget blat: locate a sequence against supported genome assemblies.
  • gget muscle: run multiple sequence alignment.
  • gget diamond: run local sequence alignment against reference sequences.
  • gget alphafold and gget pdb: inspect protein-structure references.
  • gget enrichr, gget opentargets, gget archs4, gget bgee, gget cbio, and gget cosmic: explore enrichment, target, expression, cancer, and disease association data.

Do not assume every module supports every Python version or dependency set. Some optional scientific dependencies have narrower version support than the core package.

Quick Examples

Find genes:

gget search -s human brca1 dna repair -o brca1-search.json

Fetch gene metadata:

gget info ENSG00000012048 -o brca1-info.json

Fetch a sequence:

gget seq ENSG00000012048 -o brca1-seq.fa

Run a small BLAST query:

gget blast "MEEPQSDPSVEPPLSQETFSDLWKLLPEN" -l 10 -o blast-results.json

Python example:

import gget

genes = gget.search(["BRCA1", "DNA repair"], species="human")
info = gget.info(["ENSG00000012048"])
sequence = gget.seq("ENSG00000012048")

Reproducibility Log

For scientific outputs, include enough metadata to replay the query.

| Date | gget version | Module | Query | Species/assembly | Output | Notes |
| --- | --- | --- | --- | --- | --- | --- |
| 2026-05-11 | `gget --version` | search | `BRCA1 DNA repair` | human | `brca1-search.json` | Docs checked before run |

Also record:

  • Python version and environment manager.
  • Any optional dependency installed through gget setup.
  • Database-specific identifiers returned by the query.
  • Whether output is JSON, CSV, FASTA, or a DataFrame export.
  • Any failures that were resolved by upgrading gget.

Review Checklist

  • Did you upgrade or verify the installed gget version?
  • Did you check the current upstream module docs before using arguments?
  • Is the species or assembly explicit?
  • Are identifiers preserved exactly, including Ensembl/UniProt prefixes?
  • Is the result labeled as database output rather than clinical interpretation?
  • Is the query reproducible from the saved command or Python snippet?
  • Are optional dependencies installed in an isolated environment?

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.