clinvar-variation-skill

Submit compact ClinVar Clinical Tables and NCBI Variation requests for search, VCV, RCV, SCV, and RefSNP lookups. Use when a user wants variant-level summaries or identifier mapping

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

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.

The body is a tight, well-structured overview that points to one real script and gives an executable example plus clear I/O contracts. Its main weaknesses are mild action-list duplication and a single example covering only the search case.

Suggestions

Show one short executable example for a vcv/rcv/scv/refsnp lookup in addition to the search example so all common cases are demonstrated.

De-duplicate the action enumeration: list action→endpoint mapping once and reference it from Input/Output instead of restating it.

Make the failure/retry loop explicit (e.g., on ok=false, inspect error.code, then re-run) rather than only hinting at re-runs.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no conceptual padding, but the action-type list (search/vcv/rcv/scv/refsnp) is restated across Execution behavior, Input, and Output sections, a minor redundancy that could be trimmed.	4 / 5
Actionability	Provides a concrete, copy-pasteable bash example and explicit input/output field specs, but only the search action is demonstrated; vcv/rcv/scv/refsnp invocations are described but not shown, leaving a gap versus covering all common cases.	4 / 5
Workflow Clarity	The single-action flow (parse action + required fields, execute, return summary or save raw, failures return ok=false) is unambiguous for this read-only skill, though an explicit validate/retry loop is only hinted via 'Re-run requests' rather than spelled out.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (Operating rules, Execution behavior, Input, Output, Execution, References) and a single one-level-deep, real bundle reference (scripts/clinvar_variation.py, confirmed present); the References section explicitly states no further files are needed.	5 / 5
	Total	17 / 20 Passed

Description

83%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.

The description is concise, third-person, and clearly pairs a concrete capability statement with an explicit 'Use when...' trigger, scoring well on completeness. Trigger-term coverage and distinctiveness are strong but not maximal due to a few missing natural synonyms and minor generic-word overlap.

Suggestions

Add the natural synonyms users say, e.g. 'rsID / rs number' alongside RefSNP and 'ClinVar Variation ID' alongside VCV, to broaden trigger coverage.

Tighten the generic terms ('search', 'identifier mapping') with ClinVar-scoped qualifiers to reduce overlap risk with unrelated skills.

Dimension	Reasoning	Score
Specificity	Names the ClinVar/NCBI Variation domain and several concrete actions (search, VCV, RCV, SCV, RefSNP lookups), but the actions are all 'lookup' variants rather than a diverse set, leaving minor coverage gaps relative to the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (submit ClinVar Clinical Tables and NCBI Variation requests for the listed lookups) and 'when' via a concrete 'Use when a user wants variant-level summaries or identifier mapping' trigger clause.	5 / 5
Trigger Term Quality	Good natural keyword coverage for the target audience (ClinVar, VCV, RCV, SCV, RefSNP, variant-level summaries, identifier mapping), but misses common synonyms users say such as 'rsID'/'rs number' (only RefSNP appears) and 'ClinVar Variation ID'.	4 / 5
Distinctiveness Conflict Risk	The ClinVar/NCBI Variation niche is clearly distinct with specific identifier triggers, but generic phrasing like 'search' and 'identifier mapping' carries minor overlap risk with general search or ID-mapping skills.	4 / 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/clinvar-variation-skill/SKILL.md
Commit: 1dc1958

Reviewed: 5 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.