CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-polygenic-risk-score

Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Calculates genetic risk profiles, interprets PRS percentiles, and assesses disease predisposition across conditions including type 2 diabetes, coronary artery disease, and Alzheimer's disease. Use when asked to calculate polygenic risk scores, interpret genetic risk for complex diseases, build custom PRS from GWAS data, or answer questions like "What is my genetic predisposition to breast cancer?"

59

Quality

67%

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 ./skills/bio/tooluniverse-polygenic-risk-score/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

The body is information-rich and well-sectioned but bloated with genomics tutorials Claude already knows, monolithic with no progressive disclosure, and lacking validation checkpoints in the workflow. The actionable code examples are the strongest element but stop short of copy-paste completeness.

Suggestions

Strip the tutorial 'Key Concepts' and 'Limitations and Considerations' sections down to what Claude doesn't already know about GWAS/LD/effect sizes, keeping only PRS-specific methodology and ToolUniverse tool usage.

Move References/Resources and the extended Best Practices and Ethics content into separate reference files (e.g. references/methods.md, references/ethics.md) and link to them one level deep from a lean overview.

Add explicit validation/verification steps to the workflow — e.g., check that association queries returned genome-wide-significant SNPs and confirm QC-filtered SNP counts before computing the final PRS — with a fix-and-retry loop.

DimensionReasoningScore

Conciseness

The body teaches concepts Claude already knows — 'GWAS (Genome-Wide Association Studies)' study design, 'Linkage Disequilibrium', effect-size/odds-ratio primers (β=0.5 kg/m², OR=1.5), and multi-section Limitations/Ethics tutorials — padding the token budget with textbook explanation.

1 / 3

Actionability

Provides concrete function calls with real parameters (build_polygenic_risk_score(trait=..., p_threshold=5e-8, max_snps=1000), calculate_personal_prs, interpret_prs_percentile), but they are wrapper-style invocations with no imports/tool registration shown, so they are not fully copy-paste ready.

2 / 3

Workflow Clarity

A clear 6-step sequence (Trait Selection → Risk Interpretation) is present, but there are no validation/feedback checkpoints for the batch SNP-QC and scoring steps, capping the score at 2 per the rubric.

2 / 3

Progressive Disclosure

A single ~390-line monolithic file holds Key Concepts, References, Limitations, and Best Practices inline with no bundle files or one-level-deep references; sections are organized but content that should be split is not.

2 / 3

Total

7

/

12

Passed

Description

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.

A strong description: third person, concrete capabilities, explicit 'Use when' triggers with natural user phrasing, and a distinct niche. No significant weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build and interpret polygenic risk scores', 'Calculates genetic risk profiles', 'interprets PRS percentiles', 'assesses disease predisposition' — matching the score-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both 'what' (build/interpret PRS, calculate profiles, percentiles) and 'when' via a clear 'Use when...' clause with concrete triggers.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would say ('calculate polygenic risk scores', 'interpret genetic risk', 'What is my genetic predisposition to breast cancer?'), giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (PRS from GWAS summary statistics) with distinct triggers unlikely to overlap with unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wu-yc/LabClaw
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.