Skip to main content
NeVibeCode · repository · 39 items

science-skills: a set by google-deepmind

The google-deepmind/science-skills repository on GitHub: 39 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

About the repository

GitHub
google-deepmind/science-skills
Stars
★ 3,512
Installs across cards
91,450
License
Apache-2.0
Source updated
2026-11-10
In the catalog since
2026-10-25
literature-search-arxiv skill literature-search-arxiv searches arXiv for papers and preprints, returns metadata and abstracts, and downloads full text as PDF, HTML or LaTeX source. CX Codex +1 3,700installs literature-search-openalex skill literature-search-openalex queries the OpenAlex database to find research papers, download open-access PDFs, and collect citation metrics via a local CLI. Handy for resolving DOIs and tracking author publications. CX Codex +1 3,400installs pubmed-database skill pubmed-database gives your agent a CLI into PubMed and PubMed Central: search papers, pull abstracts and full text, link publications to biological databases. CX Codex +1 3,000installs literature-search-europepmc skill literature-search-europepmc searches Europe PMC for scientific papers, downloads open-access full texts and PDFs, and pulls citation and reference lists. CX Codex +1 2,800installs literature-search-biorxiv skill literature-search-biorxiv is a Claude Code skill that retrieves bioRxiv and medRxiv preprint metadata by DOI or date range. Keyword and author filters need a short date window and a category. CX Codex +1 2,700installs clinical-trials-database skill clinical-trials-database queries ClinicalTrials.gov via REST API v2 to search studies by condition, drug, status, or phase. Saves filtered study data directly to JSON. CX Codex +1 2,600installs workflow-skill-creator skill workflow-skill-creator turns a completed agent workflow into a reusable skill. Use it when you want to package a process that has already been worked through. CX Codex +1 2,600installs embl-ebi-ols skill embl-ebi-ols — a skill for Claude Code and other agents that connects to the EMBL-EBI Ontology Lookup Service, covering 250+ ontologies including GO, DOID, and HP. CX Codex +1 2,400installs reactome-database skill reactome-database connects Reactome services for gene list enrichment, identifier mapping, and pathway exports. Useful for running biological data queries inside coding agents. CX Codex +1 2,400installs dbsnp-database skill dbsnp-database — a skill for NCBI dbSNP: resolves rsIDs from coordinates or HGVS, returns variant type, gene associations, clinical significance and allele frequencies. CX Codex +1 2,400installs protein-sequence-similarity-search skill protein-sequence-similarity-search runs a homology search on a protein sequence with MMseqs2 or BLAST, interprets the alignment metrics and writes a Markdown table of top hits. CX Codex +1 2,400installs protein-sequence-msa skill The protein-sequence-msa skill for Claude Code aligns multiple protein sequences via the EBI Clustal Omega API from a FASTA file and produces a saved alignment with identity metrics. CX Codex +1 2,400installs human-protein-atlas-database skill human-protein-atlas-database retrieves semi-quantitative protein expression levels and subcellular localisation data from the Human Protein Atlas. Useful for validating human protein presence across tissues. CX Codex +1 2,400installs opentargets-database skill The opentargets-database skill gives your agent GraphQL access to the Open Targets Platform: target-disease associations, drug data and tractability scores. CX Codex +1 2,400installs ensembl-database skill ensembl-database resolves gene symbols into ENSG, ENST and ENSP IDs, pulls sequences and predicts variant effects with VEP. Useful when genomic data lives in your terminal. CX Codex +1 2,400installs clinvar-database skill clinvar-database — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that gives the agent access to ClinVar through a Python wrapper. CX Codex +1 2,400installs chembl-database skill chembl-database — a skill that lets your agent pull molecules, targets, bioactivity, approved drugs and structure matches from ChEMBL. CX Codex +1 2,400installs alphagenome-single-variant-analysis skill alphagenome-single-variant-analysis — a skill that runs one genetic variant in chr:pos:ref>alt form through the AlphaGenome API and reports expression, chromatin and histone effects. CX Codex +1 2,400installs uniprot-database skill uniprot-database retrieves protein metadata, function annotations, and sequences from UniProtKB, UniParc, and UniRef. Useful for mapping database identifiers and streaming entries. CX Codex +1 2,400installs openfda-database skill openfda-database is a Claude Code skill that queries, counts and downloads openFDA API data for searches on FDA safety events, recalls, labels and NDCs. CX Codex +1 2,400installs pymol skill A PyMOL skill that renders protein and molecular structures, runs alignments, and measures distances or contacts. Useful when you already have a structure file and need an image or a number. CX Codex +1 2,400installs ncbi-sequence-fetch skill ncbi-sequence-fetch fetches protein and nucleotide sequences from NCBI databases via E-utilities. It queries records by accession, gene name, locus tag, PubMed ID, or patent. CX Codex +1 2,400installs pubchem-database skill pubchem-database — a skill that wires your agent into PubChem: resolves compounds by name, CID or SMILES and pulls properties, hazard data and bioactivity. CX Codex +1 2,400installs alphafold-database-fetch-and-analyze skill alphafold-database-fetch-and-analyze pulls AlphaFold predicted structures by UniProt ID and works out what they mean: pLDDT confidence, disordered regions, rigid domain boundaries. CX Codex +1 2,400installs pdb-database skill pdb-database searches and downloads experimental 3D structures of biomolecules from RCSB PDB using sequence similarity, structure comparisons, or chemical attributes. CX Codex +1 2,400installs unibind-database skill The unibind-database skill queries UniBind for experimentally validated transcription-factor binding sites and downloads BED or FASTA coordinates for local analysis. CX Codex +1 2,300installs ucsc-conservation-and-tfbs skill ucsc-conservation-and-tfbs — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that pulls evolutionary conservation scores and transcription factor binding sites from the UCSC Genome Browser. CX Codex +1 2,300installs encode-ccres-database skill encode-ccres-database queries the ENCODE Registry of cis-regulatory elements using the SCREEN GraphQL API and REST API. It identifies promoters or enhancers across cell types. CX Codex +1 2,300installs gnomad-database skill gnomad-database is a Claude Code skill that queries variant allele frequencies, gene constraint metrics and structural variants from gnomAD using Python scripts with automatic API rate limit enforcement. CX Codex +1 2,300installs quickgo-database skill quickgo-database is a Claude Code skill that queries QuickGO and the ECO ontology. It maps genes to Gene Ontology terms and explores their hierarchy. CX Codex +1 2,300installs jaspar-database skill Queries the JASPAR database for transcription factor binding profiles. Useful when fetching PFM or PWM matrices and converting gene names into stable matrix IDs. CX Codex +1 2,300installs gtex-database skill gtex-database retrieves RNA expression and eQTL data from GTEx across 54 non-diseased human tissue sites. Use it to query genes, variants, or tissue-specific expression. CX Codex +1 2,300installs foldseek-structural-search skill foldseek-structural-search sends a protein 3D structure file to the Foldseek API and returns structurally similar proteins. Built for cases where you have coordinates, not just a sequence. CX Codex +1 2,300installs interpro-database skill interpro-database queries protein domains, families, and functional sites through the InterPro API. Integrates 14 member databases and automates genome annotations with GO terms. CX Codex +1 2,300installs string-database skill The string-database skill queries STRING for protein interactions, functional enrichment, and homology. Use it when protein evidence or pathway analysis is needed. CX Codex +1 2,300installs credentials skill credentials is a Claude Code skill that checks whether a required key is in ~/.env and asks for it through hidden input instead of chat. CX Codex +1 1,600installs predictingthepast skill predictingthepast restores damaged Latin and Ancient Greek texts, estimates their origin, and retrieves parallel inscriptions. Use it when analysing an inscription or epigraphic document. CX Codex +1 1,400installs alphagenome-atlas-website-links skill alphagenome-atlas-website-links builds deep-links to the AlphaGenome Atlas for variants, loci, candidate tables and ref-vs-alt prediction views. CX Codex +1 726installs alphagenome-variant-impact-score skill alphagenome-variant-impact-score scores genetic variants with AlphaGenome Variant Impact values through the AlphaGenome Atlas API. Useful when you need to annotate a VCF or scan a window for every substitution. CX Codex +1 724installs

More in NeVibeCode

Project sponsors

Companies that keep this analytics open