variant-annotation
Query and annotate gene variants from ClinVar and dbSNP databases. Trigger when: - User provides a variant identifier (rsID, HGVS notation, genomic coordinates) and asks about clinical significance - User mentions "ClinVar", "dbSNP", "variant annotation", "pathogenicity", "clinical significance" - User wants to know if a mutation is pathogenic, benign, or of uncertain significance - User provides VCF content or variant data requiring interpretation - Input: variant ID (rs12345), HGVS notation (NM_007294.3:c.5096G>A), or genomic coordinates (chr17:43094692:G>A) - Output: clinical significance, ACMG classification, allele frequency, disease associations
87
82%
Does it follow best practices?
Impact
99%
1.26xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 an excellent skill description that clearly defines its specialized domain of genetic variant annotation. It provides comprehensive trigger conditions with specific examples of input formats and expected outputs. The use of domain-specific terminology creates clear distinctiveness while remaining accessible to users who would naturally use these terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query and annotate gene variants', with detailed input types (rsID, HGVS notation, genomic coordinates) and output types (clinical significance, ACMG classification, allele frequency, disease associations). | 3 / 3 |
Completeness | Clearly answers both what (query and annotate gene variants from ClinVar/dbSNP) and when (explicit 'Trigger when:' section with five detailed trigger conditions covering user inputs, keywords, and use cases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'ClinVar', 'dbSNP', 'variant annotation', 'pathogenicity', 'clinical significance', 'rsID', 'HGVS notation', 'VCF', 'pathogenic', 'benign', 'uncertain significance', plus concrete examples like 'rs12345'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting genetic variant databases with domain-specific terminology (ClinVar, dbSNP, ACMG, HGVS, VCF) that would not conflict with general document or data processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable content with executable code examples, comprehensive input/output documentation, and thorough ACMG classification details. However, it suffers from verbosity with unnecessary boilerplate sections (Evaluation Criteria, Lifecycle Status, Security Checklist) and could benefit from moving reference material like ACMG criteria to separate files. The workflow lacks explicit error handling and validation checkpoints for batch operations.
Suggestions
Move the ACMG Classification Criteria section to a separate ACMG_REFERENCE.md file and link to it, reducing the main skill by ~60 lines
Remove boilerplate sections (Evaluation Criteria, Lifecycle Status, Test Cases, Security Checklist) that don't provide actionable guidance for Claude
Add explicit error handling workflow: what to do when API rate limits are hit, when variants aren't found, or when HGVS parsing fails
Fill in the empty Parameter descriptions in the table (--variant, --file, --output, --delay are missing descriptions)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains substantial useful content but includes unnecessary sections like 'Evaluation Criteria', 'Lifecycle Status', and 'Test Cases' that add little value for Claude. The ACMG criteria tables are comprehensive but could be referenced externally rather than inline. | 2 / 3 |
Actionability | Provides fully executable Python code and CLI commands with clear examples. The input format table, output JSON schema, and batch query examples are copy-paste ready and cover multiple use cases. | 3 / 3 |
Workflow Clarity | While individual operations are clear, there's no explicit workflow for handling errors, validation failures, or API rate limit issues. The batch processing lacks checkpoints or validation steps between queries. | 2 / 3 |
Progressive Disclosure | References to 'references/' directory and 'requirements.txt' exist, but the ACMG criteria (50+ lines) should be in a separate reference file. The skill is monolithic with content that could be better organized across files. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.