Life-Science Database Query Skill#

This skill packages a broad set of modular sub-skills that can be composed to answer questions across every major area of life-sciences research. Each sub-skill maps to one or more public databases and carries its own operating rules and execution scripts.

When To Use This Skill#

• The user asks a broad life-sciences question ("what is known about …", "tell me about this gene/variant/compound …")
• The user wants a specific public-database lookup (gnomAD, UniProt, ChEMBL, ClinicalTrials.gov, etc.)
• The user needs multi-source evidence synthesis (genetics + expression, structure + chemistry, clinical + literature)
• The user wants locus-to-gene prioritization, PheWAS follow-up, or multi-cohort replication
• The user wants to discover public datasets or preprints for a research topic

Entry Point#

For broad or ambiguous requests, invoke research-router-skill first. It classifies the request, normalizes entities, selects the minimum useful set of downstream sub-skills, optionally parallelizes independent evidence lanes using subagents, and synthesizes the final answer.

Use a specific sub-skill directly only when the request is clearly scoped to a single source.

Sub-Skill Directory#

Sub-skill files live at skills/<sub-skill-name>/SKILL.md. Read the relevant SKILL.md before invoking any sub-skill.

Orchestration#

Sub-skillDescriptionresearch-router-skillRoute broad or ambiguous life-sciences requests to the right sub-skills, normalize entities, optionally parallelize independent evidence lanes with subagents, and synthesize a concise evidence-backed answer.

Human Genetics And Variant Evidence#

Sub-skillDescriptionopentargets-skillOpen Targets Platform GraphQL: target, disease, drug, variant, study, and associated-disease datasource heatmap data.gwas-catalog-skillGWAS Catalog REST API v2: studies, associations, SNPs, EFO traits, genes, publications, and loci.clinvar-variation-skillClinVar Clinical Tables and NCBI Variation: search, VCV, RCV, SCV, and RefSNP lookups.gnomad-graphql-skillgnomAD GraphQL: allele frequency, gene constraint, and variant-context queries.ensembl-skillEnsembl REST API: lookup, overlap, cross-reference, and variation endpoints.eva-skillEuropean Variation Archive REST: species metadata and archived variant lookups.epigraphdb-skillEpiGraphDB API: ontology, literature, Mendelian randomisation, gene-drug, and support-path evidence.genebass-gene-burden-skillGenebass gene-burden PheWAS for one Ensembl gene ID and one burden set.gtex-eqtl-skillGTEx v2 API: single-tissue eQTL associations from rsID, GRCh37, or GRCh38 input.eqtl-catalogue-skilleQTL Catalogue API: association retrieval and documented metadata endpoints.locus-to-gene-mapper-skillMulti-skill locus-to-gene prioritization chain (EFO → GWAS → coordinates → Open Targets L2G/coloc → eQTL → burden/coding context).finngen-phewas-skillFinnGen PheWAS: single-variant association summaries (GRCh38 query).ukb-topmed-phewas-skillUKB-TOPMed PheWAS: single-variant association summaries (GRCh38 query).biobankjapan-phewas-skillBioBank Japan PheWAS: single-variant association summaries (GRCh37 query).tpmi-phewas-skillTPMI PheWAS: single-variant association summaries (GRCh38 query).

Expression, Cell Context, And Functional Genomics#

Sub-skillDescriptionbgee-skillBgee SPARQL: healthy wild-type expression metadata with ontology-aware lookup patterns.human-protein-atlas-skillHuman Protein Atlas: gene JSON, search downloads, and tissue or cell-line lookups.cellxgene-skillCELLxGENE Discover API: public single-cell collection and dataset metadata.encode-skillENCODE REST API: object lookups, portal-style search, and metadata retrieval.rnacentral-skillRNAcentral API: RNA entry browsing, single-entry lookup, and cross-reference retrieval.

Protein, Structure, Pathway, And Functional Biology#

Sub-skillDescriptionalphafold-skillAlphaFold Protein Structure Database API: prediction, UniProt summary, sequence summary, and annotation lookups.rcsb-pdb-skillRCSB PDB: core metadata, Search API queries, and FASTA downloads.uniprot-skillUniProt REST API: UniProtKB, UniRef, UniParc, and FASTA stream endpoints.string-skillSTRING API: network, interaction-partner, and enrichment endpoints.quickgo-skillQuickGO: GO terms, annotations, and ontology traversal.reactome-skillReactome ContentService: pathway, event, participant, search, and diagram data.rhea-skillRhea: biochemical reaction search for reactions and reaction IDs.

Chemistry, Metabolites, And Pharmacology#

Sub-skillDescriptionbindingdb-skillBindingDB REST API: ligand-target binding lookups by PDB, UniProt, or similarity search.chembl-skillChEMBL API: activity, molecule, target, mechanism, and text-search endpoints.pubchem-pug-skillPubChem PUG REST: compound properties, descriptions, assay summaries, and substance metadata.chebi-skillChEBI 2.0 API: chemical search, compound lookup, ontology traversal, and structure metadata.pharmgkb-skillPharmGKB API: genes, variants, clinical annotations, dosing guidelines, and search.hmdb-skillHMDB: metabolite, protein, disease, and pathway search.

Clinical, Translational, And Disease Evidence#

Sub-skillDescriptionclinicaltrials-skillClinicalTrials.gov API v2: study search, metadata, enums, search areas, and field statistics.cbioportal-skillcBioPortal API: studies, molecular profiles, mutations, clinical data, and samples.civic-skillCIViC GraphQL: cancer variant interpretation schema inspection and targeted evidence retrieval.ipd-skillIPD REST: HLA allele and cell-level metadata using the public IPD query API.

Literature, Search, And Public Study Discovery#

Sub-skillDescriptionncbi-entrez-skillNCBI Entrez E-Utilities: PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows.ncbi-pmc-skillNCBI PMC Open Access: article and file availability metadata.biorxiv-skillbioRxiv and medRxiv API: preprint details, publication linkage, and DOI lookups.biostudies-arrayexpress-skillBioStudies and ArrayExpress API: free-text search and accession-based study retrieval.ncbi-datasets-skillNCBI Datasets v2: assembly, genome, taxonomy, and related metadata endpoints.ncbi-blast-skillNCBI BLAST Common URL API: submit, poll, and summarize nucleotide or protein BLAST jobs.ncbi-clinicaltables-skillClinical Tables NCBI Gene: human gene lookup, pagination, and field selection.

Multi-Omics, Proteomics, And Specialized Data Sources#

Sub-skillDescriptionpride-skillPRIDE Archive API: proteomics project discovery and project-level metadata.proteomexchange-skillProteomeXchange PROXI: datasets, libraries, peptidoforms, proteins, PSMs, spectra, and USI examples.metabolights-skillMetaboLights: study discovery and study-level metabolomics metadata.mgnify-skillMGnify API: microbiome studies, samples, and biome metadata.efo-ontology-skillEFO OLS4: search, term lookup, children, and descendants for ontology resolution.

Routing Heuristics#

Choose the minimum sub-skills needed to answer the question.

Research objectiveRecommended sub-skillsTarget or disease backgroundopentargets-skill, gwas-catalog-skill, gtex-eqtl-skill, human-protein-atlas-skillVariant interpretationclinvar-variation-skill, gnomad-graphql-skill, ensembl-skill, one or more PheWAS skillsLocus-to-gene prioritizationlocus-to-gene-mapper-skill (or its component sub-skills for custom workflows)Multi-cohort PheWAS replicationfinngen-phewas-skill, ukb-topmed-phewas-skill, biobankjapan-phewas-skill, tpmi-phewas-skillExpression and tissue contextbgee-skill, human-protein-atlas-skill, cellxgene-skill, gtex-eqtl-skillProtein structure and functionalphafold-skill, rcsb-pdb-skill, uniprot-skill, reactome-skillChemistry and pharmacologychembl-skill, bindingdb-skill, pubchem-pug-skill, pharmgkb-skillEntity normalizationefo-ontology-skill, ncbi-clinicaltables-skill, ensembl-skill, uniprot-skillClinical and cancer evidenceclinicaltrials-skill, cbioportal-skill, civic-skill, opentargets-skillLiterature and preprintsncbi-entrez-skill, ncbi-pmc-skill, biorxiv-skillPublic dataset discoverybiostudies-arrayexpress-skill, ncbi-datasets-skill, pride-skill, metabolights-skill, mgnify-skillSequence similarity searchncbi-blast-skillPathway and reaction contextreactome-skill, rhea-skill, quickgo-skill, string-skillMicrobiome contextmgnify-skillMetabolomics contextmetabolights-skill, hmdb-skillProteomics contextpride-skill, proteomexchange-skill

Subagent Guidance#

When subagents are available, use them as bounded retrieval and analysis accelerators for independent evidence lanes.

Good candidates for parallelization:

• genetics versus expression evidence for the same gene or variant
• structure versus chemistry for the same target
• literature versus clinical evidence for the same disease
• multiple PheWAS cohorts for the same variant

Keep the coordinating agent responsible for:

• interpreting the user request and defining scope
• resolving identifiers and canonical entities
• reconciling conflicting evidence across sources
• writing the final synthesis

Each subagent should receive a bounded objective and return concise findings, caveats, sources used, and any artifact paths.

Evidence Quality Notes#

• Cross-check orthogonal evidence types rather than over-indexing on one source.
• Call out ancestry limitations, tissue specificity, study design caveats, and evidence gaps explicitly.
• Treat heatmap breadth (Open Targets datasource scores) as evidence-source context, not proof of causality or direction of effect.
• For variant lookups, verify coordinate build (GRCh37 vs GRCh38) before querying cohort-specific PheWAS skills.