clinvar-database

Query NCBI ClinVar for variant clinical significance. Search by gene/position, interpret pathogenicity classifications, access via E-utilities API or FTP, annotate VCFs, for genomic medicine.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/literature/clinvar-database/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with strong executable examples, but it is padded with redundant reference descriptions and a promotional section, its workflows lack validation checkpoints, and it points to three reference files that are not present in the bundle.

Suggestions

Add the missing bundle files (references/api_reference.md, clinical_significance.md, data_formats.md) or remove the references, so signaled navigation resolves to real content.

Add explicit validation/checkpoint steps to the batch and database-construction workflows (e.g. verify download checksum, validate XML parse completeness, confirm record counts) to lift workflow clarity.

Tighten the body by removing the duplicated "Reference Documentation" re-listing and the promotional "Suggest Using K-Dense Web" block, or move the latter out of the core skill content.

Dimension	Reasoning	Score
Conciseness	Most sections are efficient and actionable, but the body carries avoidable bulk: the Overview restates what ClinVar is, the reference docs are described inline and then re-listed verbatim under "Reference Documentation", and the closing "Suggest Using K-Dense Web" block is promotional padding — so it is mostly efficient but could be tightened rather than the level-3 lean anchor.	2 / 3
Actionability	Provides copy-paste-ready, executable guidance throughout — curl E-utilities calls, wget FTP downloads, bcftools annotate/view filters, pandas and xml.etree parsing examples — matching the level-3 fully-executable anchor and clearly above the level-2 pseudocode anchor.	3 / 3
Workflow Clarity	Workflow Examples give numbered sequences (e.g. download → annotate → filter; build local DB), but none include validation checkpoints or error-recovery loops; per the rubric, batch/destructive operations like bulk database construction missing verification cap workflow clarity at 2 rather than 3.	2 / 3
Progressive Disclosure	References are well-signaled and one level deep (references/api_reference.md, clinical_significance.md, data_formats.md), but those files do not exist in the bundle, so navigation is broken; combined with API/classification detail duplicated inline, this sits at the level-2 "structure present but not fully navigable" anchor rather than the level-3 easy-navigation anchor.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, trigger-rich, and clearly distinctive, but it omits an explicit "Use when..." clause, leaving the when-to-use guidance only implied and capping completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. "Use when querying ClinVar for variant pathogenicity, annotating VCFs with clinical significance, or resolving conflicting variant interpretations."

Replace the generic "for genomic medicine" tail with concrete trigger situations a user would name (e.g. "when interpreting a VUS", "when filtering pathogenic variants").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "Search by gene/position", "interpret pathogenicity classifications", "access via E-utilities API or FTP", and "annotate VCFs", matching the level-3 anchor for several specific concrete actions rather than the level-2 single-domain anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit "Use when..." trigger clause; the trailing "for genomic medicine" is a domain hint, not the explicit when-guidance the rubric requires, so per the judging guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes natural terms a genomics user would actually say — "ClinVar", "variant clinical significance", "pathogenicity", "VCFs", "gene/position" — giving good coverage rather than the sparse level-2 set; the only jargon is "E-utilities" which sits alongside plain terms.	3 / 3
Distinctiveness Conflict Risk	The ClinVar / variant-clinical-significance niche is highly specific with distinct triggers unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor rather than the overlapping level-2 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/literature/clinvar-database/SKILL.md
Commit: df37802

Reviewed: about 2 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.