gget

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• look up this gene
• gget search
• AlphaFold structure
• gene enrichment analysis
• find gene info

What it does

gget is a Claude Code skill from K-Dense AI’s scientific-agent-skills repo. It turns Claude into a gget user for fast, interactive queries across 20+ bioinformatics databases — gene search and metadata (gget.search, gget.info), BLAST searches, AlphaFold structure retrieval (gget.alphafold), enrichment analysis (gget.enrichr), sequence alignment (gget.muscle), and ARCHS4 expression data.

A session produces Python code or CLI commands that return structured gene information, protein structures, or enrichment results in seconds — without writing API integration code.

When to use it

Reach for it when:

• You need gene metadata (gene name, synonyms, Ensembl ID, description, associated diseases) for a list of gene symbols
• You want to fetch an AlphaFold structure for a protein without navigating the AlphaFold database web UI
• You’re doing a quick enrichment analysis on a gene list (GO terms, KEGG, WikiPathways) interactively

When not to reach for it:

• Batch processing or complex multi-step pipelines where output needs to be parsed and integrated — use biopython for more control
• Multi-database programmatic integration — use bioservices

Install

Copy the SKILL.md from K-Dense AI’s gget folder into .claude/skills/gget/ in your project.

Trigger phrases: “look up this gene”, “gget search”, “AlphaFold structure”, “gene enrichment analysis”.

What a session looks like

A typical session has three phases:

1. Query specification. Provide gene symbols, Ensembl IDs, sequences, or terms to search. Claude selects the appropriate gget function and species parameter.
2. gget call. The function runs and returns a pandas DataFrame or file (PDB for AlphaFold) with structured results — no manual parsing required.
3. Downstream use. Claude helps interpret or format the results: filtering enrichment terms by adjusted p-value, extracting specific metadata fields, or visualizing the structure path for PyMOL/ChimeraX.

Receipts

Where it works well:

• Gene symbol to Ensembl ID conversion for a list of genes — gget.info() handles this for multiple species with a single call
• AlphaFold structure retrieval — gget.alphafold() downloads the predicted structure file ready for visualization without navigating the web UI

Where it backfires:

• gget’s database queries depend on external service availability; intermittent failures from Ensembl, NCBI, or other upstream APIs need error handling that gget’s simple interface doesn’t always surface clearly
• Very large gene lists may hit rate limits or timeouts on some gget backends — split into batches for reliability

Pattern that works: use gget.search() to find the right Ensembl IDs first, then pass those IDs to gget.info() for structured metadata — more reliable than searching by gene symbol alone when gene names are ambiguous across species.

Source and attribution

Originally authored by K-Dense Inc.. The canonical SKILL.md lives in the gget folder of their public scientific-agent-skills repository.

License: MIT. Install, adapt, and redistribute with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.