gtex-eqtl-skill

Fetch GTEx single-tissue eQTL associations from one variant input by accepting rsID, GRCh37, or GRCh38 input and resolving to the required GRCh38 query for the GTEx v2 API. Use when a user wants eQTL associations returned as JSON.

Quality

83%

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

78%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 concise, actionable single-purpose skill body with clear sections and appropriate offloading of logic to bundled scripts. The main improvements are reducing redundancy in the input examples and making the error/validation flow explicit.

Suggestions

Consolidate the Input section's repeated JSON object examples into a single annotated example showing all accepted keys (grch38/grch37/rsid/variant/max_results) to trim tokens.

Add one or two executable shell examples for the rsID and GRCh37 input forms, mirroring the existing grch38 command, to push actionability to fully copy-paste-ready coverage.

State the validation/error-recovery flow explicitly (e.g. malformed input -> invalid_input; resolution failure -> network_error) instead of leaving it implicit in the script.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining what eQTL/GTEx are. It is not a 5 because the Input section repeats near-identical JSON object forms and separator examples that could be consolidated.	4 / 5
Actionability	Provides a copy-paste runnable command, references the real entry script (scripts/gtex_eqtl.py), and gives concrete input/output JSON shapes. It is not a 5 because only one invocation form is shown as a shell command; rsID and GRCh37 invocations appear only as JSON, not as executable examples.	4 / 5
Workflow Clarity	The Operating rules lay out a clear sequence (accept one input -> resolve to GRCh38 -> convert to variantId -> return one JSON object) and the skill is read-only, so the destructive/batch validation cap does not apply. It is not a 5 because validation/error-handling checkpoints are only implicit in the script rather than stated in the body.	4 / 5
Progressive Disclosure	Well-organized sections (Operating rules, Input, Output, Execution) with a clear one-level-deep reference to the entry script; the implementation detail variant_resolution.py is correctly kept out of the overview, making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

87%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 specific, well-targeted description that answers both what the skill does and when to use it, using third-person voice and natural domain trigger terms. Minor room to broaden trigger synonyms, but it avoids fluff and over-claims.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Fetch GTEx single-tissue eQTL associations', 'accepting rsID, GRCh37, or GRCh38 input', 'resolving to the required GRCh38 query'). It is not a 5 because the scope is a single task rather than comprehensive coverage of multiple distinct actions.	4 / 5
Completeness	Clearly answers 'what' (fetch single-tissue eQTL associations and resolve variant inputs to a GRCh38 GTEx v2 query) and 'when' with the concrete trigger phrase 'Use when a user wants eQTL associations returned as JSON'.	5 / 5
Trigger Term Quality	Includes natural domain keywords users would say ('GTEx', 'eQTL', 'rsID', 'GRCh37', 'GRCh38', 'variant', 'JSON') plus an explicit 'Use when a user wants eQTL associations returned as JSON' trigger. A few synonyms are missing (e.g. 'expression quantitative trait loci'), so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GTEx v2 single-tissue eQTL lookup) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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/gtex-eqtl-skill/SKILL.md
Commit: 1dc1958

Reviewed: 6 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.