CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-polygenic-risk-score

Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Covers PRS construction (clumping/thresholding, PRS-CS), validation in independent cohorts, ancestry-aware adjustment, and clinical interpretation (population-relative risk, not absolute prediction). Use for PRS-based risk stratification.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-polygenic-risk-score in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

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

The body is well-structured with concrete tooling and code examples, but it pads token budget with foundational genetics concepts Claude already knows and lacks explicit validation feedback loops in its batch-oriented workflow. Splitting background material into reference files and adding verification checkpoints would lift the weaker dimensions.

Suggestions

Move the 'Key Concepts' section (GWAS, LD, effect sizes, population stratification) into a references file or trim to only PRS-specific nuance Claude would not already know, to improve conciseness.

Add explicit validation checkpoints to the workflow — e.g., verify the association count returned, confirm SNP filtering removed strand-ambiguous variants, and check the score distribution before interpretation — to lift workflow clarity above the batch-operation cap of 3.

Split the Applications and Limitations material into a separate reference file linked from a brief inline summary, reducing the monolithic inline content for stronger progressive disclosure.

DimensionReasoningScore

Conciseness

The methodology, data-source, and workflow sections are efficient and domain-specific, but the 'Key Concepts' section re-explains foundational genetics (what GWAS is, linkage disequilibrium, odds ratios, beta coefficients, population stratification) that Claude already knows, adding noticeable padding.

3 / 5

Actionability

Provides concrete code examples with parameters (build_polygenic_risk_score, calculate_personal_prs, interpret_prs_percentile), named tools (gwas_get_associations_for_trait, run_ldsc_heritability), and specific QC thresholds (MAF < 0.01, HWE p < 1e-6), though some tool signatures are partly assumed rather than fully specified.

4 / 5

Workflow Clarity

A clear six-step workflow is sequenced, but this batch operation (building a score across hundreds of SNPs) lacks explicit validation checkpoints or error-recovery feedback loops, which caps workflow clarity at 3 per the batch-operation guideline.

3 / 5

Progressive Disclosure

Well-organized section headers and no nested/deep references give good internal structure, but the ~280-line body inlines substantial background (Key Concepts, Applications) that could be split into separate files, leaving minor organization gaps.

4 / 5

Total

14

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 concise yet comprehensive, naming concrete capabilities and methods with an explicit 'Use for' trigger clause in third person. It clearly distinguishes this skill's niche and would be triggered by the natural phrasings users employ for PRS work.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — build and interpret PRS, construction via clumping/thresholding and PRS-CS, validation in independent cohorts, ancestry-aware adjustment, and clinical interpretation — giving comprehensive coverage rather than generic phrasing.

5 / 5

Completeness

Explicitly answers both 'what' (build and interpret PRS with named methods) and 'when' via the concrete trigger clause 'Use for PRS-based risk stratification.'

5 / 5

Trigger Term Quality

Uses the natural terms a user would actually say for this domain — 'polygenic risk scores (PRS)', 'GWAS summary statistics', 'risk stratification' — with the canonical acronym and full phrase both present.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PRS construction and interpretation) with a distinct trigger phrase, making overlap with other skills minimal.

5 / 5

Total

20

/

20

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
mims-harvard/ToolUniverse
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.