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.
86
83%
Does it follow best practices?
Impact
88%
1.15xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is a strong, technically specific description that clearly identifies the skill's domain (ClinVar/clinical genomics) and lists concrete capabilities. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others. The domain-specific terminology provides excellent distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about variant pathogenicity, ClinVar lookups, clinical significance of mutations, or needs to annotate variants with clinical data.'
Consider adding common user phrasings like 'is this variant pathogenic', 'check ClinVar', or 'variant interpretation' to improve trigger matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query NCBI ClinVar', 'Search by gene/position', 'interpret pathogenicity classifications', 'access via E-utilities API or FTP', 'annotate VCFs'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'for genomic medicine' at the end hints at context but doesn't explicitly state when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'ClinVar', 'variant', 'clinical significance', 'gene', 'pathogenicity', 'VCF', 'genomic medicine', 'E-utilities'. These cover domain-specific terms a bioinformatician or clinician would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific domain terms like 'ClinVar', 'pathogenicity classifications', 'VCF annotation', and 'E-utilities API'. These are unique to clinical genomics and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent code examples and clear workflows. The main weakness is verbosity - it explains concepts Claude already knows (what ClinVar is, what classifications mean) and includes sections like 'When to Use This Skill' that add little value. The progressive disclosure and workflow clarity are strong, with appropriate references to detailed documentation.
Suggestions
Remove the 'Overview' and 'When to Use This Skill' sections - Claude doesn't need to be told what ClinVar is or when to use this skill
Trim explanatory text around classifications (e.g., '~99% probability') - Claude understands pathogenicity concepts
Consolidate the 'Important Limitations' section into brief bullet points rather than categorized subsections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., explaining what ClinVar is, what VUS means) that Claude would already know. The content is reasonably organized but could be tightened significantly - the 'When to Use This Skill' section and some explanatory text add tokens without adding value. | 2 / 3 |
Actionability | Excellent executable code examples throughout - curl commands, Python scripts with xml.etree, bcftools commands, pandas examples, and bash one-liners. All examples are copy-paste ready with specific file paths, parameters, and realistic use cases. | 3 / 3 |
Workflow Clarity | The workflow examples section provides clear numbered steps with explicit commands at each stage. Example 2 (VCF annotation) shows a complete pipeline with download, annotate, and filter steps. The conflict resolution strategy provides a clear decision sequence. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to separate documentation files (references/api_reference.md, references/clinical_significance.md, references/data_formats.md). The main skill provides overview and quick examples while pointing to detailed references for comprehensive information. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- 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.