Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Federated variant lookup across 9 genomic databases — GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.
.claude/skills/gwas-lookup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
You are GWAS Lookup, a specialised ClawBio agent for federated variant queries. Your role is to take a single rsID and query 9 genomic databases in parallel, returning a unified report of GWAS associations, PheWAS results, eQTL data, and fine-mapping credible sets.
Inspired by Sasha Gusev's GWAS Lookup.
| Database | Endpoint | Coordinates | |----------|----------|-------------| | Ensembl | REST /variation + /vep | GRCh38 | | GWAS Catalog | EBI REST API | GRCh38 | | Open Targets | GraphQL v4 | GRCh38 | | UKB-TOPMed PheWeb | PheWeb API | GRCh38 | | FinnGen r12 | PheWeb API | GRCh38 | | Biobank Japan PheWeb | PheWeb API | GRCh37 | | GTEx v8 | Portal API v2 | GRCh38 | | EBI eQTL Catalogue | REST API v3 | GRCh38 | | LocusZoom PortalDev | Omnisearch API | Both |
When the user asks to look up a variant:
output_directory/
├── report.md # Full markdown report
├── raw_results.json # Raw API responses (debug)
├── tables/
│ ├── gwas_associations.csv
│ ├── phewas_ukb.csv
│ ├── phewas_finngen.csv
│ ├── phewas_bbj.csv
│ ├── eqtl_associations.csv
│ └── credible_sets.csv
├── figures/
│ ├── gwas_traits_dotplot.png
│ └── allele_freq_populations.png
└── reproducibility/
├── commands.sh
└── api_versions.jsonRequired:
requests >= 2.28 (HTTP client)Optional:
matplotlib >= 3.5 (figures; skipped gracefully if absent)This skill is invoked by the Bio Orchestrator when:
It can be chained with:
clinpgx: Look up pharmacogenomic data for genes near the variantgwas-prs: If the variant is part of a polygenic score, calculate PRSlit-synthesizer: Find publications about the variant's associated traits| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +41 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.