CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/clinvar-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 as an overview with a real, correctly-shaped bundle, but the executable guidance is incomplete: the flagship annotate example has a hidden prerequisite (clinvar.vcf.gz / --clinvar), bulk retrieval has no command, and no workflow includes validation. Minor redundancy between Key Features and Implementation Details adds avoidable tokens.

Suggestions

Make the annotate example runnable as printed: document the ClinVar VCF prerequisite, show the '--clinvar' flag, and add a one-line command for fetching the ClinVar VCF from the FTP URL already in references/api_reference.md.

Replace the prose-only bulk download section ('Supports obtaining ClinVar datasets via FTP') with an executable command (e.g., wget from ftp://ftp.ncbi.nlm.nih.gov/pub/clinvar/vcf_GRCh38/) and link references/api_reference.md at that point.

Trim the hedging sentences ('Output is expected to include...', 'Designed for pipeline use: ...') and the Key Features / Implementation Details overlap, and add a validation checkpoint after annotation (e.g., verify output with 'bcftools view -h annotated.vcf').

DimensionReasoningScore

Conciseness

The body is mostly list-based with no conceptual padding, but includes trimmable hedging ('Output is expected to include matching ClinVar records/identifiers', 'Designed for pipeline use: deterministic input/output files', 'Recommended when you need reproducible, high-throughput annotation') and the 'Key Features' section substantially restates 'Implementation Details' ('ClinVar search via NCBI E-utilities' appears in both). This matches anchor 3 — mostly efficient but could be tightened — rather than anchor 4, where over-explanation is only a minor instance.

3 / 5

Actionability

Two copy-paste-ready commands with real query syntax are given ('python scripts/search.py --term "BRCA1[gene] AND pathogenic[CLNSIG]"', 'python scripts/annotate.py --input input.vcf --output annotated.vcf'), but key details are missing: the annotate command silently requires a 'clinvar.vcf.gz' file and an undocumented '--clinvar' flag (scripts/annotate.py defaults to 'clinvar.vcf.gz'), bulk download has no command or URL despite being a key feature, and the interpretation workflow stops at 'see references/clinical_significance.md' with no follow-up step. This fits anchor 3 — some concrete guidance but incomplete, missing key details — better than anchor 4's 'minor gaps'.

3 / 5

Workflow Clarity

Rough sequences exist (search → interpret; download → annotate) via per-feature example commands, but there are no explicit steps connecting them and no validation checkpoints — nothing tells the user to verify the annotated VCF (e.g., with bcftools) or how to obtain the ClinVar VCF prerequisite. Per the rubric's cap, batch operations (whole-VCF annotation, bulk downloads) without validation steps cannot score above 3, and the implicit-checkpoint profile matches anchor 3 exactly.

3 / 5

Progressive Disclosure

The body is a genuine overview (~60 lines) pointing to a real, well-organized bundle: both referenced files exist and are one level deep ('references/api_reference.md', 'references/clinical_significance.md'), scripts are referenced by path, and the reference files contain no nested pointers. It falls short of anchor 5 on a minor organization gap: the bulk-download section mentions FTP but never signals that the FTP URLs and directory layout live in references/api_reference.md, and the reference pointers appear only under 'Key Features' rather than at the point of need.

4 / 5

Total

13

/

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 strong description: concrete capabilities, explicit 'use when' trigger phrases, and a well-defined niche around a named database. The only gap is that bulk/FTP retrieval, advertised as a key feature in the body, is not reflected in the description.

DimensionReasoningScore

Specificity

The description names the domain ('querying the NCBI ClinVar database') and several concrete actions ('retrieve variant records, clinical significance, and phenotype relationships', 'annotating VCF files with ClinVar annotations'), matching the anchor 'lists several specific actions; minor gaps in coverage'. It is not a 5 because bulk dataset retrieval — one of the skill's five key features — is absent from the description, leaving a minor coverage gap.

4 / 5

Completeness

It explicitly answers both questions: what ('Utilities for querying the NCBI ClinVar database to retrieve variant records, clinical significance, and phenotype relationships') and when ('use when searching variants by gene/condition/significance, interpreting Pathogenic/Benign/VUS classifications, or annotating VCF files with ClinVar annotations') with concrete trigger phrases — a direct match for the anchor-5 good example.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: 'searching variants by gene/condition/significance', 'interpreting Pathogenic/Benign/VUS classifications', 'annotating VCF files', 'ClinVar' — good keyword coverage matching anchor 4. It falls short of anchor 5 because common variations users would say — variant lookup by 'rsID', the '.vcf' file extension, or 'ACMG' — are missing.

4 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche — ClinVar is a specifically named database with distinct triggers (variant classification, VUS, ClinVar annotation) and minimal overlap risk with other skills, matching the anchor-5 example's profile of a focused database utility with distinct triggers.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.