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

96%

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

92%Weight 40%Scale 1-3

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

The body is concise and highly actionable with executable commands and a clear prerequisite workflow, but progressive disclosure has a gap: the bundled references/citation.bib file is never navigated or signaled from the body.

Suggestions

Add a pointer to references/citation.bib in the References section (e.g., a 'Citation' entry) so the bundled reference file is discoverable from the body.

Distinguish bundle references from external URLs in the References section, or rename/relabel it to avoid the implication that only external links are referenced.

Optionally mention the citation file's purpose (e.g., cite Karczewski et al. 2020 when reporting gnomAD results) so its inclusion is justified.

Dimension	Reasoning	Score
Conciseness	Lean body with no concept explanations (no 'what is gnomAD' padding), compact command blocks, and terse argument notes; it assumes Claude's competence and every section earns its place.	3 / 3
Actionability	Provides fully executable `uv run scripts/...` commands with by-variant-ID, by-rsID, region, and gene forms, plus concrete output field names (pli, oe_lof_upper, faf95/faf99) — copy-paste ready.	3 / 3
Workflow Clarity	Prerequisites are sequenced (uv setup then license notification) with an explicit condition-then-action checkpoint for the license file, and the querying tasks are single-action scripts that are unambiguous per the simple-skills note.	3 / 3
Progressive Disclosure	Scripts are well-signaled via absolute-path instructions, but the bundle file references/citation.bib is not referenced anywhere in the body (the 'References' section lists only external URLs), leaving a provided reference undiscoverable.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong description: concise, third-person, with explicit 'Use when' triggers, concrete capabilities, and clear disambiguation from sibling databases. It cleanly satisfies all four dimensions without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the API surface (allele frequency, constraint metrics pLI/LOEUF, region/gene variant search, structural variants), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Query the Genome Aggregation Database...') and when ('Use when determining the rarity...') with explicit triggers, plus a 'Don't use for...' exclusion clause.	3 / 3
Trigger Term Quality	Uses natural genomics phrasings a user would actually say ('rarity or allele frequency', 'gene constraint metrics', 'pLI, LOEUF', 'loss-of-function intolerance', 'structural variants'), giving good coverage rather than just jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (gnomAD allele frequencies/constraint) with explicit disambiguation against adjacent tools ('use COSMIC' for somatic cancer, 'use ENA' for raw reads), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 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: 0b42509

Reviewed: 8 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.