tooluniverse-variant-interpretation
Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability.
npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-variant-interpretation --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis.
How it works
The skill specifies a multi-phase workflow:
- Phase 1: Variant Identity & Normalization: standardize HGVS, map to gene/transcripts/protein, determine consequence type.
- Phase 2: Clinical Database Queries: query ClinVar, gnomAD, OMIM, ClinGen gene validity and dosage sensitivity, and optionally COSMIC and DisGeNET for broader context.
- Phase 2.5: Regulatory context for non-coding variants (ChIPAtlas, ENCODE, conservation, regulatory impact).
- Phase 3: Computational Predictions: gather SIFT/PolyPhen, CADD, SpliceAI, and conservation data.
- Phase 4: Structural Analysis (for VUS/novel missense): obtain protein structure (PDB/AlphaFold2), map variant, assess domain/site impact, predict destabilization.
- Phase 4.5: Expression Context: cell-type expression and tissue relevance.
- Phase 5: Literature Evidence: PubMed functional studies, preprints, case reports, and segregation data.
- Phase 6: ACMG Classification: apply evidence codes, calculate classification, note limitations, and generate clinical recommendations.
When to use it
Use when users ask about variant interpretation or classification, have VCF data needing clinical annotation, seek ACMG classification, want structural impact analysis for missense variants, or inquire about pathogenicity of specific variants.
What it can touch
Employs tools including myvariant_query, Ensembl_get_variant_info, NCBI_gene_search, clinvar_search, gnomad_search, OMIM_search, OMIM_get_entry, ClinGen_gene_validity, ClinGen_search_dosage_sensitivity, COSMIC_search_mutations, DisGeNET_search_gene, ClinGen_search_actionability, SpliceAI_predict_splice, SpliceAI_get_max_delta. The workflow references function calls and tool usage as explicit steps, and maps data through sextets of data sources and predictions to support ACMG decision making.
Caveats
No explicit license text summarized beyond listing; the skill declares NOASSERTION. The workflow relies on external databases with their own update cycles and review statuses; results depend on data availability and currency. No outcomes are promised; the implementation provides a framework to generate ACMG classifications and clinical recommendations based on integrated evidence.
--- name: tooluniverse-variant-interpretation description: Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability. --- # Clinical Variant Interpreter Systematic variant interpretation skill using ToolUniverse - from raw variant calls to ACMG-classified clinical recommendations with structural impact analysis. --- ## Problem This Skill Solves Clinical labs and researchers face critical challenges in variant interpretation: 1. **Variant classification uncertainty** - VUS (Variants of Uncertain Significance) comprise 40-60% of clinical variants 2. **Evidence aggregation burden** - Must integrate data from 10+ databases per variant 3. **Structural context missing** - Traditional annotation ignores 3D protein impact 4. **Clinical actionability un
- Problem This Skill Solves
- Key Principles
- Triggers
- Workflow Overview
- Phase Details
- Phase 1: Variant Identity & Normalization
- Phase 2: Clinical Database Queries
- 2.1 COSMIC for Somatic Context (NEW)
- 2.2 OMIM Gene-Disease Context (NEW)
- 2.3 DisGeNET Gene-Disease Evidence (NEW)
- 2.4 ClinGen Gene Validity & Dosage Sensitivity (NEW)
- 2.5 SpliceAI Splice Variant Prediction (NEW)
- Phase 2.5: Regulatory Context (NEW - for Non-Coding Variants)
- Phase 3: Computational Predictions (ENHANCED)
What does the tooluniverse-variant-interpretation skill do?
Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill tooluniverse-variant-interpretation --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.