CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-pathway-disease-genetics

Connect GWAS variants to biological pathways and druggable targets. Maps GWAS hits to causal genes (via fine-mapping/eQTL), then to pathways (Reactome, KEGG, WikiPathways), then to existing drugs hitting those pathways. Use for pathway-level disease mechanisms, druggable-pathway prioritization from GWAS, SNP-to-pathway-to-target tracing, and tissue-specific eQTL evidence for drug target hypotheses.

69

Quality

83%

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

The canonical home for this skill is tooluniverse-pathway-disease-genetics in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

A well-organized, highly actionable body with concrete tool calls and a clear three-step workflow, weakened mainly by lack of progressive disclosure (no reference files) for a complex skill and some implicit validation checkpoints.

Suggestions

Add at least one complete runnable Python example under 'COMPUTE, DON'T DESCRIBE' (e.g. calling gwas_get_variants_for_trait and summarizing hits with pandas) to lift actionability from concrete commands to copy-paste code.

Move the detailed tool catalog and Key Parameter Gotchas into a references/ file (e.g. TOOL_REFERENCE.md) and link to it from SKILL.md, keeping the body as an overview to improve progressive disclosure.

Insert explicit validation checkpoints in the Three-Step Workflow (e.g. after enrichment, verify FDR/convergence before proceeding to druggability) to add the missing feedback loops.

Trim the genetics-101 explanations in Core Reasoning Principles to the reasoning chain only, dropping restatements of what non-coding variants or eQTLs are.

DimensionReasoningScore

Conciseness

Mostly lean and terse with imperative style and dense gotchas, but a few genetics-101 explanations ('Non-coding GWAS variants rarely affect the nearest gene', the TCF7L2/Wnt walkthrough) restate concepts Claude already knows and could be trimmed.

4 / 5

Actionability

Concrete tool calls with exact parameters and format gotchas (e.g. 'identifiers is space-separated STRING, not array') cover common cases, but there is no full runnable Python code block despite the 'COMPUTE, DON'T DESCRIBE' directive.

4 / 5

Workflow Clarity

A clearly sequenced Three-Step Workflow with evidence tiers and ranking formulas, but validation/feedback checkpoints are implicit rather than explicit (no validate→fix→retry loops), leaving minor gaps.

4 / 5

Progressive Disclosure

Internally well-sectioned with clear headers, but for a complex multi-phase skill the detailed tool catalog and gotchas are fully inlined with no reference files (references/scripts/assets are absent), so content that could be split out stays inline.

3 / 5

Total

15

/

20

Passed

Description

96%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.

A strong, specific description that clearly states a multi-step capability and an explicit 'Use for' trigger clause with concrete domain keywords. The only soft spot is minor overlap with closely related sub-skills listed in the body.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the full pipeline — 'Connect GWAS variants to biological pathways and druggable targets', 'Maps GWAS hits to causal genes (via fine-mapping/eQTL)', 'then to pathways (Reactome, KEGG, WikiPathways)', 'then to existing drugs hitting those pathways' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (the gene→pathway→drug mapping pipeline) and 'when' via the 'Use for pathway-level disease mechanisms, druggable-pathway prioritization from GWAS, SNP-to-pathway-to-target tracing...' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural domain terms a genomics user would actually say: 'GWAS variants', 'druggable targets', 'causal genes', 'eQTL', 'pathway-level disease mechanisms', 'SNP-to-pathway-to-target tracing', plus named databases (Reactome, KEGG, WikiPathways).

5 / 5

Distinctiveness Conflict Risk

Carves a clear end-to-end GWAS→pathway→drug-target niche with distinct triggers, but the body's Related Skills (gwas-trait-to-gene, gene-enrichment, drug-target-validation) cover sub-pieces, creating minor overlap risk.

4 / 5

Total

19

/

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.