RepoAI
Browse MCPs

ClinVar Database

88TrustedShips scripts

Clinical pathogenicity classifications and interpretation evidence for human genomic variants.

What it does

ClinVar Database provides direct access to the standard consensus records for human genetic variation. It delivers authoritative pathogenicity labels, such as Pathogenic or VUS, derived from global laboratory assertions, allowing assistants to ground their analysis in established clinical evidence.

By incorporating this skill, the assistant gains the ability to retrieve specific rationales, review statuses, and associated conditions for variants. It manages complex data parsing and API rate limiting, ensuring that queries for detailed variant records or gene-wide lists remain accurate and consistent.

When it earns its place

Reach for it when…

This skill is suited for verifying the clinical significance of a specific variant, comparing conflicting laboratory interpretations, or assembling lists of variants that meet precise pathogenicity criteria within a target gene or region.

Look elsewhere when…

Do not use this for exploring the population frequency of variants, investigating the normal physiological function of gene products, or generating structural predictions for mutated proteins, as these tasks require dedicated demographic or molecular biology data sources.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • What is the clinical classification of this BRCA1 variant?
  • Find all pathogenic variants in the HBB gene.
  • Are there any conflicting interpretations for this specific mutation?
  • Show me the assertion criteria for this variant classification.

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/clinvar_database ~/.claude/skills/clinvar-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/clinvar_database .claude/skills/clinvar-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

ClinVar Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →