variant-pathogenicity-predictor
Integrate REVEL, CADD, PolyPhen-2, SIFT, and MutationTaster scores to predict variant pathogenicity with ACMG guideline interpretation.
72
Quality
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/variant-pathogenicity-predictor/SKILL.mdQuality
Discovery
67%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 description excels at specificity and distinctiveness by naming five specific bioinformatics tools and the ACMG framework, creating a clear technical niche. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords beyond the technical tool names.
Suggestions
Add a 'Use when...' clause specifying trigger conditions, e.g., 'Use when analyzing genetic variants, assessing mutation impact, or interpreting clinical significance of variants.'
Include natural language trigger terms users might say, such as 'variant analysis', 'mutation pathogenicity', 'clinical variant interpretation', or 'genetic variant scoring'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Integrate REVEL, CADD, PolyPhen-2, SIFT, and MutationTaster scores' and 'predict variant pathogenicity with ACMG guideline interpretation' - these are specific bioinformatics tools and standards. | 3 / 3 |
Completeness | Clearly describes WHAT it does (integrate scores, predict pathogenicity, interpret ACMG guidelines), but lacks explicit WHEN guidance - no 'Use when...' clause or trigger conditions specified. | 2 / 3 |
Trigger Term Quality | Includes domain-specific tool names (REVEL, CADD, PolyPhen-2, SIFT, MutationTaster) and technical terms (pathogenicity, ACMG), but missing common user phrases like 'variant analysis', 'mutation scoring', or 'clinical interpretation'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche in computational genetics/bioinformatics with specific tool names and ACMG standards - very unlikely to conflict with other skills due to its technical specificity. | 3 / 3 |
Total | 10 / 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 strong actionable guidance with executable commands, clear parameter documentation, and well-defined score thresholds. However, it suffers from a generic workflow that lacks domain-specific validation checkpoints (e.g., VCF format validation, score retrieval verification), and the content could be more concise by removing redundant sections and splitting detailed templates into separate files.
Suggestions
Add explicit validation checkpoints to the workflow: validate VCF format before processing, verify all requested scores were retrieved before classification, and confirm no conflicting evidence before final pathogenicity call.
Remove redundancy between 'Output Requirements' and 'Response Template' sections - consolidate into a single, concise output specification.
Make the workflow section specific to variant pathogenicity prediction rather than generic task execution (e.g., '1. Parse variant coordinates 2. Query each scoring tool 3. Apply thresholds 4. Check for conflicting evidence 5. Generate ACMG classification').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., the response template and output requirements sections overlap significantly, and the workflow section is generic rather than specific to this tool). The integrated scores table and parameters are appropriately concise. | 2 / 3 |
Actionability | Provides fully executable bash commands with clear parameter documentation, specific score thresholds in a table format, and concrete examples for both single variant and batch VCF processing. The fallback template gives actionable structure for error cases. | 3 / 3 |
Workflow Clarity | The workflow section is present but generic (could apply to any tool). Missing explicit validation checkpoints between steps - for example, no step to validate VCF format before processing or verify score retrieval succeeded before classification. The fallback template partially compensates but validation gaps remain. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The detailed response template, output requirements, and risk assessment sections could be split into separate reference files for a cleaner overview. No external file references are provided. | 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.