Tooluniverse Variant Interpretation

This is a comprehensive clinical genomics workflow that takes you from raw variant calls to ACMG-classified pathogenicity reports with structural context. It orchestrates 40+ bioinformatics tools (ClinVar, gnomAD, AlphaFold2, CADD, SpliceAI, CIViC) through a six-phase pipeline: variant normalization, database lookup, computational prediction, structural analysis, literature review, and final ACMG classification. The workflow is opinionated about looking things up rather than guessing, uses MANE Select transcripts by default, and includes regulatory context for non-coding variants. Built for molecular tumor boards and return-of-results reporting where you need defensible evidence codes, not just a score.

skills.sh installs: 353
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-variant-interpretation --agent claude-code

Installs into .claude/skills of the current project.

Files

Clinical Variant Interpreter

Systematic variant interpretation using ToolUniverse - from raw variant calls to ACMG-classified clinical recommendations with structural impact analysis.

Triggers

Use this skill when users:

Ask about variant interpretation, classification, or pathogenicity
Have VCF data needing clinical annotation
Need ACMG classification for variants
Want structural impact analysis for missense variants

Key Principles

ACMG-Guided - Follow ACMG/AMP 2015 guidelines with explicit evidence codes
Structural Evidence - Use AlphaFold2 for novel structural impact analysis
Population Context - gnomAD frequencies with ancestry-specific data
Actionable Output - Clear recommendations, not just classifications
English-first queries - Always use English terms in tool calls; respond in user's language

LOOK UP, DON'T GUESS

When asked about a variant's significance, query ClinVar/gnomAD/CIViC FIRST. Never classify a variant without checking databases. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.