RepoAI
Browse MCPs

gnomAD Database

88TrustedShips scripts

Retrieve population allele frequencies and gene constraint metrics from gnomAD.

What it does

Installing Gnomad Database provides your assistant with direct programmatic access to the Genome Aggregation Database, allowing it to pull population genetics data during a conversation. Instead of forcing you to manually browse web interfaces for variant metrics, the assistant fetches specific frequency or constraint data directly from the official API.

This skill enables precise, evidence-based discussions about genetic variation by anchoring claims in large-scale reference cohorts. It ensures that allele frequencies and intolerance scores are retrieved using standard conventions, minimizing errors associated with manual data entry or lookup.

When it earns its place

Reach for it when…

Use this to determine how rare a specific genetic variant is within large reference populations or to assess if a gene is intolerant to loss-of-function mutations using pLI and LOEUF scores. It is ideal for researchers needing to contextualize findings in specific genes or genomic regions during variant interpretation tasks.

Look elsewhere when…

Do not use this for clinical diagnostics involving individual patient genomes, as it does not perform variant calling or annotation on custom sequencing data. It is also unsuitable for tracking somatic mutations found in oncology studies or for retrieving raw sequencing files, which require specialized clinical databases or sequence read archives.

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 population allele frequency for variant 1-55516888-G-GA?
  • Check the LOEUF score and pLI for the TP53 gene.
  • List all missense variants reported in the BRCA1 gene.
  • Find variants in the region between chromosome 1 positions 50000 and 60000.

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/gnomad_database ~/.claude/skills/gnomad-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/gnomad_database .claude/skills/gnomad-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

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

How skills and MCP servers differ →