SkillFoxx

Science Skills

A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology

  • 3,466 ★ on the repository
  • Last commit
  • Apache-2.0
SkillEditors’ pick

Extended access

Why this level

  • Skills run scripts and reach external scientific services
  • Some sources require API keys and send queries outward
All reasons and checks

google-deepmind/science-skillsAuthor:Google DeepMind

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/science-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Skills run scripts and reach external scientific services
  • Some sources require API keys and send queries outward

This is third-party code. Review the repository files before installing.

What it does

A collection of more than thirty skills that connect an agent to scientific databases and tools. It covers AlphaGenome, the AlphaFold structure database, UniProt, PDB, Ensembl, ChEMBL, PubChem, ClinVar, gnomAD, GTEx and other genomics, structural biology and chemistry resources. A separate group of skills searches literature in arXiv, bioRxiv, Europe PMC, OpenAlex and PubMed. Some skills drive PyMOL or run structural search through Foldseek. Each skill is a folder with a SKILL.md, helper scripts and reference files; dependencies install through uv, and some sources need an API key.

Who it is for. For researchers, bioinformaticians and analysts who run scientific workflows through an AI agent.

Good fit when

  • You need gene, protein or compound data from a domain database
  • You need to find and process scientific papers on a topic
  • You need to analyze a protein structure or run a structural search

Not a fit when

  • The task is not scientific and domain databases are not needed
  • You cannot obtain API keys for sources such as AlphaGenome and OpenAlex

Example request

Look up BRCA1 in UniProt and find recent papers about it

Limitations

The skills rely on external scientific services whose availability and limits depend on the source. Some skills, such as AlphaGenome and OpenAlex, require an API key; others work better with a key but still return data without one. Dependencies install through uv, and on first run the agent asks to approve the install. Individual data sources carry their own licenses and terms of use, and the user is responsible for following them. The project is not an official Google product.

How to disable. Remove the installed skill set from the agent's skills directory. In Google Antigravity disable the Science plugin in settings.

FAQ

Do I need Google Antigravity?

No. The set installs into any skill-aware agent via npx skills add. In Antigravity it is also available as the built-in Science plugin.

Do all skills require a key?

No. Many databases are open and work without a key. A key is needed for AlphaGenome and OpenAlex, and for some sources it only raises request limits.

Discussion

No questions or reviews yet.

Skills

17 skills for computational biology: RNA-seq, single-cell, protein structure, docking, literature and figures

SkillExtended access75
Editors’ pick

166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases

SkillExtended access57K

Around 200 skills for Claude Code on bioinformatics, chemistry and biostatistics, from RNA-seq analysis to molecular docking

SkillExtended access388

A library of agent skills for medical research: literature search and appraisal, study design, data analysis and academic writing

SkillExtended access2K

37 skills for computational drug discovery: from target selection and docking to ADMET and the clinical record.

PluginExtended access55

README in short

The README describes a set of skills for scientific work across genomics, structural biology, chemistry and literature search. Each skill has a SKILL.md with instructions, a scripts folder with helper code and, where needed, references. The set installs via npx skills add or connects as the Science plugin in Google Antigravity, with uv handling dependencies. Some skills need API keys, and individual data sources have their own licenses. Code is Apache 2.0, materials are CC-BY, and the project is not an official Google product.

README badge

Original SKILL.md

---
name: uniprot-database
description: >-
  Access protein metadata, function, taxonomy, and sequences across UniProtKB,
  UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or
  retrieving functional annotations and publications. Don't use for sequence
  alignment, protein folding, or sequence similarity search (use specialized
  skills for those tasks).
---

# UniProt Database Access

## Prerequisites

1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure
    `uv` is installed and on PATH.
2.  **User Notification**: If .licenses/uniprot_database_LICENSE.txt does not
    already exist in the workspace root directory then (1) prominently notify
    the user to check the terms at https://www.uniprot.org/help/license and
    https://www.uniprot.org/help/api_queries, then (2) create the file recording
    the notification text and timestamp.

## Overview

Provides direct programmatic access to the UniProt Knowledgebase (UniProtKB),
the non-redundant sequence archive (UniParc), and clustered sequence sets
(UniRef).

Report a problem