gnomad-graphql-skill

Submit compact gnomAD GraphQL requests for frequency, gene constraint, and variant context queries. Use when a user wants concise gnomAD summaries

Quality

81%

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

85%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 content is concise, actionable, and well-structured for a simple single-purpose skill, with executable code and a correctly referenced script bundle. The main gap is workflow clarity: while the single action is unambiguous, it lacks an explicit validation/verification checkpoint for interpreting the script's success/error output before reporting to the user.

Suggestions

Add a brief verification step such as 'After running, check `ok`; if false, surface `error.code` and stop rather than summarizing' to create an explicit feedback loop around the external API call.

Clarify how to choose between `query` and `query_path` with a one-line rule (e.g., use `query_path` for queries over ~N lines) so the selection is fully deterministic rather than left to judgment.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — bullet rules, an executable example, and field lists with no padding about what GraphQL or gnomAD is; every section earns its place.	3 / 3
Actionability	Provides a copy-paste-ready executable command ('echo ... \| python scripts/gnomad_graphql.py'), names the script, and lists concrete input fields with a worked JSON example, giving fully executable guidance.	3 / 3
Workflow Clarity	It is a simple single-action skill so sequence is unambiguous, but there is no validation/verification checkpoint for the network call or error recovery beyond listing error codes; for an operation that hits an external API and returns data, an explicit 'check ok=true / handle graphql_error before summarizing' feedback loop is missing.	2 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references, and the body is well-organized into clear sections (Operating rules, Execution behavior, Input, Output, Execution, References) with a single real bundle file (scripts/gnomad_graphql.py) correctly referenced.	3 / 3
	Total	11 / 12 Passed

Description

77%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.

The description is strong: it states concrete capabilities, includes an explicit 'Use when' trigger, and occupies a clear niche unlikely to conflict with other skills. The main weakness is trigger-term coverage, which leans on the single phrase 'gnomAD summaries' and omits common natural phrasings users might actually say.

Suggestions

Broaden trigger terms to natural user phrasings such as 'gnomAD lookup', 'allele/population frequency', or 'gene constraint metrics' so the skill surfaces for more varied requests.

Consider naming the data source explicitly in the trigger ('gnomAD database') alongside the tool name to improve discovery when users reference the source rather than the API.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'frequency, gene constraint, and variant context queries' — naming the specific gnomAD query types rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Submit compact gnomAD GraphQL requests for frequency, gene constraint, and variant context queries') and when ('Use when a user wants concise gnomAD summaries'), matching the rubric's good example with a clear 'Use when' trigger.	3 / 3
Trigger Term Quality	'gnomAD', 'frequency', 'gene constraint', and 'variant' are relevant domain terms, but the trigger clause ('when a user wants concise gnomAD summaries') misses common natural variations a user would say like 'allele frequency', 'population frequency', or 'gnomAD lookup'.	2 / 3
Distinctiveness Conflict Risk	The gnomAD GraphQL niche is highly specific with a distinct trigger ('gnomAD summaries'); it is unlikely to conflict with other skills or trigger incorrectly.	3 / 3
	Total	11 / 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: openai/plugins
Path: plugins/life-science-research/skills/gnomad-graphql-skill/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.