ensembl-skill

Submit compact Ensembl REST API requests for lookup, overlap, cross-reference, and variation endpoints. Use when a user wants concise Ensembl summaries

Quality

92%

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

100%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.

A well-structured, concise, and fully actionable skill body for a single-purpose REST wrapper. It avoids concept padding, gives executable examples, and references a real bundle file.

Dimension	Reasoning	Score
Conciseness	Lean bullet sections with no over-explanation of REST or Ensembl concepts; every line (base_url, max_items guidance, header suggestions) earns its place.	3 / 3
Actionability	Provides a fully executable bash example with complete JSON, concrete endpoint paths, and explicit input/output field lists — copy-paste ready.	3 / 3
Workflow Clarity	A simple single-action skill (stdin JSON -> script -> markdown summary) whose action is unambiguous; it is read-only so no destructive-operation validation loop is required.	3 / 3
Progressive Disclosure	Under 50 lines with well-organized sections and a single one-level-deep reference (scripts/rest_request.py) that exists as a real file.	3 / 3
	Total	12 / 12 Passed

Description

85%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 tight, third-person description that clearly states its purpose and trigger. Trigger-term breadth is the main weakness, as it leans on 'Ensembl summaries' rather than enumerating common user phrasings.

Suggestions

Broaden the 'Use when' trigger to mention natural user phrasings like 'looking up a gene, getting variants, or fetching Ensembl overlap/xrefs data'.

Consider including 'Ensembl ID', 'gene lookup', or 'variant' as trigger keywords to improve discovery.

Dimension	Reasoning	Score
Specificity	Names four concrete endpoint actions — 'lookup, overlap, cross-reference, and variation endpoints' — in third-person imperative voice, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states what it does (submit Ensembl REST API requests) and when to use it via an explicit 'Use when a user wants concise Ensembl summaries' clause.	3 / 3
Trigger Term Quality	'Ensembl' is a natural keyword, but the trigger clause narrows to 'concise Ensembl summaries' and omits common user phrasings such as gene, variant, or Ensembl ID, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Ensembl REST API) with a distinctive term unlikely to trigger for unrelated skills.	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/ensembl-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.