gnomad-database

Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable skill body built around three executable helper scripts with concrete invocation patterns and a clear prerequisite sequence. The main gaps are the absence of explicit output-verification/error-handling steps and an unreferenced citation.bib bundle file.

Suggestions

Add a brief verification/error-handling note for query results (e.g., how to detect API errors or empty responses in the output JSON), which would lift workflow_clarity toward 5.

Reference references/citation.bib from the body (e.g., a 'Citation' line in the References section) so the bundle file is discoverable rather than orphaned.

Fix the 'Grpmax Filtering AF' typo (likely 'GnomAD' / 'grpmax') to avoid confusing the consumer of the output field name.

Dimension	Reasoning	Score
Conciseness	Lean and operational — no basic-concept padding; the only explanatory sentence (FAF definition) is domain-specific detail needed to interpret output fields, so every token earns its place.	5 / 5
Actionability	Each of the three utilities ships copy-paste-ready commands with exact script paths, flags, and placeholders (variant ID, rsID, gene, region, consequence), covering the common cases.	5 / 5
Workflow Clarity	Prerequisites are sequenced (uv setup, then license-file check) and each script's action is unambiguous, but there are no explicit verification or error-handling steps for query results — a minor validation gap below the score-5 anchor.	4 / 5
Progressive Disclosure	Clear sections (Prerequisites, Core Rules, Utility Scripts, References) with scripts one level deep and well-signaled, but references/citation.bib exists as an orphan bundle file never referenced from the body — a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, well-scoped description that clearly states what the skill does and when to use it, with strong trigger-term coverage and explicit negative boundary guidance to avoid mis-triggering. Voice is third-person/imperative with no first/second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'determining the rarity or allele frequency', 'retrieving gene constraint metrics (pLI, LOEUF)', 'finding variants in a genomic region or gene', 'querying structural variants' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers 'what' ('Query the Genome Aggregation Database (gnomAD)' plus actions) and 'when' ('Use when determining...'), with concrete trigger phrases and negative boundary guidance.	5 / 5
Trigger Term Quality	Comprehensive natural domain vocabulary (allele frequency, genetic variants, pLI, LOEUF, structural variants, somatic mutations, sequencing reads) with synonyms (rarity/allele frequency) that a genomics user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (gnomAD queries) with distinct triggers and explicit disambiguation ('Don't use for... use COSMIC... use ENA'), minimizing conflict with related skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/gnomad_database/SKILL.md
Commit: 6883275

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.