← Back to Skills Marketplace
31
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install life-science-database-query
Description
General life-sciences research copilot bundling 50 modular sub-skills across human genetics, variant interpretation, functional genomics, expression, pathway...
README (SKILL.md)
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/\x3Csub-skill-name>/SKILL.md. Read the relevant SKILL.md before invoking any sub-skill.
Orchestration
| Sub-skill | Description |
|---|---|
research-router-skill |
Route 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-skill | Description |
|---|---|
opentargets-skill |
Open Targets Platform GraphQL: target, disease, drug, variant, study, and associated-disease datasource heatmap data. |
gwas-catalog-skill |
GWAS Catalog REST API v2: studies, associations, SNPs, EFO traits, genes, publications, and loci. |
clinvar-variation-skill |
ClinVar Clinical Tables and NCBI Variation: search, VCV, RCV, SCV, and RefSNP lookups. |
gnomad-graphql-skill |
gnomAD GraphQL: allele frequency, gene constraint, and variant-context queries. |
ensembl-skill |
Ensembl REST API: lookup, overlap, cross-reference, and variation endpoints. |
eva-skill |
European Variation Archive REST: species metadata and archived variant lookups. |
epigraphdb-skill |
EpiGraphDB API: ontology, literature, Mendelian randomisation, gene-drug, and support-path evidence. |
genebass-gene-burden-skill |
Genebass gene-burden PheWAS for one Ensembl gene ID and one burden set. |
gtex-eqtl-skill |
GTEx v2 API: single-tissue eQTL associations from rsID, GRCh37, or GRCh38 input. |
eqtl-catalogue-skill |
eQTL Catalogue API: association retrieval and documented metadata endpoints. |
locus-to-gene-mapper-skill |
Multi-skill locus-to-gene prioritization chain (EFO → GWAS → coordinates → Open Targets L2G/coloc → eQTL → burden/coding context). |
finngen-phewas-skill |
FinnGen PheWAS: single-variant association summaries (GRCh38 query). |
ukb-topmed-phewas-skill |
UKB-TOPMed PheWAS: single-variant association summaries (GRCh38 query). |
biobankjapan-phewas-skill |
BioBank Japan PheWAS: single-variant association summaries (GRCh37 query). |
tpmi-phewas-skill |
TPMI PheWAS: single-variant association summaries (GRCh38 query). |
Expression, Cell Context, And Functional Genomics
| Sub-skill | Description |
|---|---|
bgee-skill |
Bgee SPARQL: healthy wild-type expression metadata with ontology-aware lookup patterns. |
human-protein-atlas-skill |
Human Protein Atlas: gene JSON, search downloads, and tissue or cell-line lookups. |
cellxgene-skill |
CELLxGENE Discover API: public single-cell collection and dataset metadata. |
encode-skill |
ENCODE REST API: object lookups, portal-style search, and metadata retrieval. |
rnacentral-skill |
RNAcentral API: RNA entry browsing, single-entry lookup, and cross-reference retrieval. |
Protein, Structure, Pathway, And Functional Biology
| Sub-skill | Description |
|---|---|
alphafold-skill |
AlphaFold Protein Structure Database API: prediction, UniProt summary, sequence summary, and annotation lookups. |
rcsb-pdb-skill |
RCSB PDB: core metadata, Search API queries, and FASTA downloads. |
uniprot-skill |
UniProt REST API: UniProtKB, UniRef, UniParc, and FASTA stream endpoints. |
string-skill |
STRING API: network, interaction-partner, and enrichment endpoints. |
quickgo-skill |
QuickGO: GO terms, annotations, and ontology traversal. |
reactome-skill |
Reactome ContentService: pathway, event, participant, search, and diagram data. |
rhea-skill |
Rhea: biochemical reaction search for reactions and reaction IDs. |
Chemistry, Metabolites, And Pharmacology
| Sub-skill | Description |
|---|---|
bindingdb-skill |
BindingDB REST API: ligand-target binding lookups by PDB, UniProt, or similarity search. |
chembl-skill |
ChEMBL API: activity, molecule, target, mechanism, and text-search endpoints. |
pubchem-pug-skill |
PubChem PUG REST: compound properties, descriptions, assay summaries, and substance metadata. |
chebi-skill |
ChEBI 2.0 API: chemical search, compound lookup, ontology traversal, and structure metadata. |
pharmgkb-skill |
PharmGKB API: genes, variants, clinical annotations, dosing guidelines, and search. |
hmdb-skill |
HMDB: metabolite, protein, disease, and pathway search. |
Clinical, Translational, And Disease Evidence
| Sub-skill | Description |
|---|---|
clinicaltrials-skill |
ClinicalTrials.gov API v2: study search, metadata, enums, search areas, and field statistics. |
cbioportal-skill |
cBioPortal API: studies, molecular profiles, mutations, clinical data, and samples. |
civic-skill |
CIViC GraphQL: cancer variant interpretation schema inspection and targeted evidence retrieval. |
ipd-skill |
IPD REST: HLA allele and cell-level metadata using the public IPD query API. |
Literature, Search, And Public Study Discovery
| Sub-skill | Description |
|---|---|
ncbi-entrez-skill |
NCBI Entrez E-Utilities: PubMed, Gene, Protein, Nucleotide, PMC metadata, and GEO metadata workflows. |
ncbi-pmc-skill |
NCBI PMC Open Access: article and file availability metadata. |
biorxiv-skill |
bioRxiv and medRxiv API: preprint details, publication linkage, and DOI lookups. |
biostudies-arrayexpress-skill |
BioStudies and ArrayExpress API: free-text search and accession-based study retrieval. |
ncbi-datasets-skill |
NCBI Datasets v2: assembly, genome, taxonomy, and related metadata endpoints. |
ncbi-blast-skill |
NCBI BLAST Common URL API: submit, poll, and summarize nucleotide or protein BLAST jobs. |
ncbi-clinicaltables-skill |
Clinical Tables NCBI Gene: human gene lookup, pagination, and field selection. |
Multi-Omics, Proteomics, And Specialized Data Sources
| Sub-skill | Description |
|---|---|
pride-skill |
PRIDE Archive API: proteomics project discovery and project-level metadata. |
proteomexchange-skill |
ProteomeXchange PROXI: datasets, libraries, peptidoforms, proteins, PSMs, spectra, and USI examples. |
metabolights-skill |
MetaboLights: study discovery and study-level metabolomics metadata. |
mgnify-skill |
MGnify API: microbiome studies, samples, and biome metadata. |
efo-ontology-skill |
EFO OLS4: search, term lookup, children, and descendants for ontology resolution. |
Routing Heuristics
Choose the minimum sub-skills needed to answer the question.
| Research objective | Recommended sub-skills |
|---|---|
| Target or disease background | opentargets-skill, gwas-catalog-skill, gtex-eqtl-skill, human-protein-atlas-skill |
| Variant interpretation | clinvar-variation-skill, gnomad-graphql-skill, ensembl-skill, one or more PheWAS skills |
| Locus-to-gene prioritization | locus-to-gene-mapper-skill (or its component sub-skills for custom workflows) |
| Multi-cohort PheWAS replication | finngen-phewas-skill, ukb-topmed-phewas-skill, biobankjapan-phewas-skill, tpmi-phewas-skill |
| Expression and tissue context | bgee-skill, human-protein-atlas-skill, cellxgene-skill, gtex-eqtl-skill |
| Protein structure and function | alphafold-skill, rcsb-pdb-skill, uniprot-skill, reactome-skill |
| Chemistry and pharmacology | chembl-skill, bindingdb-skill, pubchem-pug-skill, pharmgkb-skill |
| Entity normalization | efo-ontology-skill, ncbi-clinicaltables-skill, ensembl-skill, uniprot-skill |
| Clinical and cancer evidence | clinicaltrials-skill, cbioportal-skill, civic-skill, opentargets-skill |
| Literature and preprints | ncbi-entrez-skill, ncbi-pmc-skill, biorxiv-skill |
| Public dataset discovery | biostudies-arrayexpress-skill, ncbi-datasets-skill, pride-skill, metabolights-skill, mgnify-skill |
| Sequence similarity search | ncbi-blast-skill |
| Pathway and reaction context | reactome-skill, rhea-skill, quickgo-skill, string-skill |
| Microbiome context | mgnify-skill |
| Metabolomics context | metabolights-skill, hmdb-skill |
| Proteomics context | pride-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.
Usage Guidance
Install only if you are comfortable with a broad networked research helper. Use it with public, non-sensitive research inputs, avoid passing Authorization/Cookie headers or private tokens, and do not enable save_raw or raw_output_path unless you choose a safe temporary location and understand that full API responses will remain on disk.
Capability Tags
Capability Assessment
Purpose & Capability
The stated purpose is public life-science database lookup and synthesis, which explains outbound API access. However many sub-skills use a generic REST client that accepts caller-supplied base URLs, absolute paths, methods, headers, request bodies, and raw output paths instead of enforcing the documented database endpoint.
Instruction Scope
The SKILL.md files usually tell the agent to use specific public database base URLs and concise summaries, and I did not find hidden role-change or prompt-injection instructions. The runtime input surface still exposes broad optional fields that bypass those intended scopes if misused.
Install Mechanism
The package is a static bundle of markdown instructions and Python scripts, with no observed auto-start, cron, shell persistence, or installer mutation. One sub-skill suggests installing the common requests dependency if missing.
Credentials
Network access is proportionate for public database querying, but unrestricted outbound destinations, caller-controlled headers, POST bodies, and broad routing across many sources exceed what a database-specific skill needs.
Persistence & Privilege
Multiple scripts support save_raw and create parent directories before writing full API responses to /tmp or a caller-specified path, without path containment. NCBI scripts also read optional NCBI API key environment variables, though those appear limited to hardcoded NCBI endpoints.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install life-science-database-query - After installation, invoke the skill by name or use
/life-science-database-query - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the life-science-database-query skill.
- Bundles 50 modular sub-skills covering human genetics, variant interpretation, functional genomics, expression, protein structure, chemistry, clinical evidence, literature, and public study discovery.
- Provides both a research-router for broad, multi-database queries and direct sub-skill invocation for targeted lookups.
- Designed to synthesize multi-source evidence across major life-science databases for research questions of varying complexity.
Metadata
Frequently Asked Questions
What is Life Science Database Query?
General life-sciences research copilot bundling 50 modular sub-skills across human genetics, variant interpretation, functional genomics, expression, pathway... It is an AI Agent Skill for Claude Code / OpenClaw, with 31 downloads so far.
How do I install Life Science Database Query?
Run "/install life-science-database-query" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Life Science Database Query free?
Yes, Life Science Database Query is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Life Science Database Query support?
Life Science Database Query is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Life Science Database Query?
It is built and maintained by SciMiner (@sciminer); the current version is v1.0.0.
More Skills