bgee-skill

Submit compact Bgee SPARQL requests for healthy wild-type expression metadata and ontology-aware lookup patterns. Use when a user wants concise Bgee summaries; save raw results only on request.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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, well-structured skill body that gives executable guidance and clear sections for a single-purpose SPARQL client. The two minor deductions stem from a near-empty References section and only one demonstrated execution example.

Suggestions

Remove or shrink the References section since it only states that no references are needed; the 'scripts/sparql_request.py' mention in Operating rules already conveys the bundle.

Add one more runnable execution example covering a SELECT-with-LIMIT case to match the breadth of the input patterns listed.

Consider a one-line note on how to interpret the summary fields (record_count_returned vs record_count_available) to make outputs more actionable.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining SPARQL or Bgee basics, but the References section ('No additional runtime references are required; keep the import package limited...') spends tokens stating an absence, which could be trimmed.	4 / 5
Actionability	Provides a copy-paste executable command ('echo ... \| python scripts/sparql_request.py'), concrete input JSON examples, and a documented output/error shape, but only one full execution example is shown despite multiple input patterns being listed.	4 / 5
Workflow Clarity	As a simple single-purpose skill, the single action (read one JSON object from stdin and run the script) is unambiguous, with operating rules ('Start with small SELECT or ASK queries and add LIMIT early') supplying clear sequencing guidance; no destructive or batch validation cap applies.	5 / 5
Progressive Disclosure	The body is well-organized into clearly labeled sections under 50 lines and references the real bundle file 'scripts/sparql_request.py' appropriately, but the dedicated References section adds little navigational value by declaring no references exist, keeping it just below the clean 5.	4 / 5
	Total	17 / 20 Passed

Description

78%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 clear, third-person description that concretely states the skill's purpose and gives an explicit 'Use when' trigger for a well-defined niche. It is held back from the top band only by a single trigger phrase and somewhat overlapping action verbs.

Suggestions

Broaden the 'Use when' clause to list multiple concrete triggers, e.g. 'Use when a user wants Bgee expression summaries, healthy wild-type lookup, or ontology-aware gene expression queries.'

Add natural synonyms users might say (e.g. 'gene expression data', 'healthy tissue expression') to widen trigger-term coverage.

Vary the action verbs so the capabilities read as distinct rather than overlapping variants of submitting queries.

Dimension	Reasoning	Score
Specificity	Names the Bgee SPARQL domain plus several concrete actions ('Submit compact Bgee SPARQL requests', 'healthy wild-type expression metadata', 'ontology-aware lookup patterns', 'save raw results'), but the actions are all query-related variations rather than a broad action set, so it stops short of comprehensive 5-level coverage.	4 / 5
Completeness	Explicitly answers both what ('Submit compact Bgee SPARQL requests...') and when ('Use when a user wants concise Bgee summaries'), but the when clause offers only a single trigger rather than the multiple concrete trigger phrases that define a 5.	4 / 5
Trigger Term Quality	Includes natural phrases a user might say ('concise Bgee summaries', 'Bgee SPARQL'), giving good keyword coverage, but lacks common synonyms or variations such as 'gene expression data' or 'expression in healthy tissues'.	4 / 5
Distinctiveness Conflict Risk	Targets a clearly distinct niche (Bgee SPARQL healthy wild-type expression) with specific triggers, making overlap with other skills minimal.	5 / 5
	Total	17 / 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: openai/plugins
Path: plugins/life-science-research/skills/bgee-skill/SKILL.md
Commit: 1e28582

Reviewed: 9 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.