CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-gwas-trait-to-gene

Discover causal genes for diseases/traits from GWAS data using Open Targets L2G (locus-to-gene) scoring — integrates eQTL, chromatin interaction, and distance evidence. Use for trait-to-gene mapping, drug-target hypothesis generation from GWAS, and replacing the 'nearest gene' heuristic with multi-evidence L2G scores.

59

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-gwas-trait-to-gene/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 thorough, well-organized skill with concrete tools and useful gotchas, but it over-explains known concepts, lacks explicit validation checkpoints in its batch workflow, and inlines catalog/schema content that belongs in reference files.

Suggestions

Add an explicit validation step to the workflow (e.g., verify returned p-values against the threshold and reconcile client/server filtering) with a fix-and-retry loop, since trait discovery aggregates many associations.

Trim background explanations Claude already knows (genome-wide significance rationale, definitions of positional vs fine-mapping) and move the 11-tool GWAS Catalog list plus the output schema into a bundled reference file.

Replace the discover_gwas_genes() pseudocode in Best Practices with actual executable tool calls so all example code is runnable.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete tool lists and code, but contains background concept explanations Claude already knows (e.g., genome-wide significance rationale, what fine-mapping/positional mapping are) and verbose example-output blocks that pad the token budget.

3 / 5

Actionability

Provides concrete, mostly executable tool calls and Python snippets (e.g., gwas_search_associations, requests/pandas bulk download), with specific parameter guidance; minor gaps such as the discover_gwas_genes() pseudocode examples not being defined as a real callable.

4 / 5

Workflow Clarity

A numbered workflow is present and confidence-level gating is defined, but it operates over a batch/aggregation of associations without explicit validation checkpoints or feedback loops for verifying results; the cap for batch operations without validation applies.

3 / 5

Progressive Disclosure

Reasonably sectioned and references one external skill (tooluniverse-data-wrangling), but it inlines a large tool catalog and output schema that would better live in separate reference files, and no bundle files are present to offload them.

3 / 5

Total

13

/

20

Passed

Description

78%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 names concrete evidence types, states a clear niche, and provides an explicit 'Use for' trigger clause. Minor room to add more natural synonyms and slightly more explicit 'when' phrasing.

DimensionReasoningScore

Specificity

Lists several concrete actions (discover causal genes, integrate eQTL/chromatin/distance evidence, L2G scoring, drug-target hypothesis generation) but frames them at a moderate level of granularity rather than enumerating many distinct concrete operations.

4 / 5

Completeness

Clearly states what it does (L2G scoring integrating multiple evidence) and gives an explicit 'Use for ...' trigger clause covering three scenarios; the 'when' could be marginally more explicit but is clearly present.

4 / 5

Trigger Term Quality

Good natural keywords ('trait-to-gene mapping', 'drug-target hypothesis generation from GWAS', 'nearest gene heuristic') that a user might say, though it leans slightly technical and omits some common synonyms.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (Open Targets L2G trait-to-gene from GWAS) with distinct triggers and explicit differentiation from the 'nearest gene' heuristic, minimizing conflict risk.

5 / 5

Total

17

/

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.