clinvar-database

Utilities for querying the NCBI ClinVar database to retrieve variant records, clinical significance, and phenotype relationships; use when searching variants by gene/condition/significance, interpreting Pathogenic/Benign/VUS classifications, or annotating VCF files with ClinVar annotations.

Quality

86%

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

72%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 well-structured and mostly actionable, with good progressive disclosure via real reference files and scripts. Its main weaknesses are mild cross-section redundancy, an unexplained hidden dependency in the annotation example, and absent validation steps for a batch annotation operation.

Suggestions

Merge the overlapping 'Key Features' and 'Implementation Details' descriptions of search/annotation into a single section to remove redundancy and tighten token use.

Show how to obtain the ClinVar VCF used for annotation (e.g., the bulk FTP download path from references/api_reference.md) or pass it via --clinvar, so the annotate example is fully executable end-to-end.

Add a verification step to the annotation workflow, such as confirming the output VCF is valid and that annotations were applied (e.g., a bcftools view/validate check), to satisfy validation expectations for a batch operation.

Dimension	Reasoning	Score
Conciseness	Avoids tutorial padding about what VCF/bcftools/E-utilities are, but the 'Key Features' and 'Implementation Details' sections restate the same search/annotation descriptions, a redundancy that could be trimmed; fits the 'efficient, minor instances of over-explanation' anchor rather than the fully lean 5.	4 / 5
Actionability	Provides two concrete, mostly copy-paste commands ('python scripts/search.py --term ...', 'python scripts/annotate.py --input ... --output ...'), but the annotation example hides an unexplained dependency (the script defaults clinvar_vcf to 'clinvar.vcf.gz') so it is not fully executable end-to-end, leaving it just below the 5 anchor.	4 / 5
Workflow Clarity	Operations are presented as independent example commands rather than a sequenced workflow, and the body omits any validation/verification step or feedback loop for VCF annotation, a batch operation; per the batch-operation cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Clear overview with well-signaled, one-level-deep references to real bundle files ('references/api_reference.md', 'references/clinical_significance.md') and scripts, with content appropriately split into separate reference files and easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

100%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 excellent: it concisely states concrete capabilities and pairs them with an explicit, trigger-rich 'use when' clause targeted at a well-defined genomics niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'querying the NCBI ClinVar database to retrieve variant records, clinical significance, and phenotype relationships', 'searching variants by gene/condition/significance', 'interpreting Pathogenic/Benign/VUS classifications', 'annotating VCF files' — with comprehensive coverage, matching the 5 anchor rather than the 4 anchor (no meaningful coverage gaps).	5 / 5
Completeness	Explicitly answers both 'what' ('Utilities for querying the NCBI ClinVar database to retrieve...') and 'when' ('use when searching variants by gene/condition/significance, interpreting... or annotating VCF files') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain trigger terms a genomics user would say — 'gene/condition/significance', 'Pathogenic/Benign/VUS classifications', 'VCF files', 'ClinVar annotations' — with synonyms (condition/phenotype) and the VCF file extension, fitting comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (NCBI ClinVar clinical-variant querying/annotation) with distinct triggers; minimal risk of firing for an unrelated skill.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/clinvar-database/SKILL.md
Commit: 63c61d3

Reviewed: 3 hours 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.