Name: tooluniverse-regulatory-variant-analysis
Rating: 69.6 (1 reviews)
Author: mims-harvard

tooluniverse-regulatory-variant-analysis

Non-coding/regulatory variant interpretation — GWAS association lookup, eQTL evidence (GTEx), chromatin state (ENCODE), regulatory variant scoring (RegulomeDB, CADD), and TF-binding disruption. Use for non-coding GWAS hit interpretation, eQTL-based gene assignment, and regulatory mechanism reasoning. Distinct from coding-variant tools.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-regulatory-variant-analysis in mims-harvard/ToolUniverse

Quality

Content

75%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-structured, actionable skill body with a clear phased workflow, concrete tool parameters, and useful fallback loops. Main gaps are example executability (pseudocode calls vs. runnable Python) and modest over-explanation of domain basics.

Suggestions

Make at least one example workflow a fully executable Python/Bash snippet (with imports and actual tool calls) to honor the 'COMPUTE, DON'T DESCRIBE' directive and lift actionability.

Trim the histone-mark glossary in the reasoning section to just the interpretation-relevant signal (active vs poised vs silenced) since Claude already knows the marks.

Consider moving the per-phase tool reference (Phases 1-4) into a separate references file, leaving SKILL.md as a tighter overview, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes domain competence, but a few interpretive glosses (e.g., enumerating which histone mark means what) edge slightly past what a genomics-aware model needs.	4 / 5
Actionability	Concrete tool names with exact parameter names and gotchas ('variant_id, not rsid', 'assay_title="TF ChIP-seq"') and step-by-step example workflows, but examples are call pseudocode rather than the fully executable copy-paste Python the 'COMPUTE, DON'T DESCRIBE' header implies.	4 / 5
Workflow Clarity	A clear seven-phase sequence with a flow diagram and a Fallback Strategies section providing error-recovery feedback loops; this is read-only analysis so the destructive-validation cap does not apply, but there is no formal per-phase validation checklist.	4 / 5
Progressive Disclosure	Well-organized into clear sections with no bundle files present; the per-phase tool reference is inlined where a separate reference file could carry the bulk, a minor organization gap keeping it just below a top score.	4 / 5
	Total	16 / 20 Passed

Description

92%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 actions and tools, gives explicit 'use for' trigger guidance, and proactively distinguishes itself from coding-variant skills. Only minor room for improvement on trigger synonym breadth.

Dimension	Reasoning	Score
Specificity	Lists five concrete capabilities with named tools — 'GWAS association lookup', 'eQTL evidence (GTEx)', 'chromatin state (ENCODE)', 'regulatory variant scoring (RegulomeDB, CADD)', 'TF-binding disruption' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (enumerated actions) and 'when' ('Use for non-coding GWAS hit interpretation...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural domain phrases a genomics user would say ('non-coding GWAS hit interpretation', 'eQTL-based gene assignment', 'regulatory mechanism reasoning'), but lacks the synonym/extension breadth of a top anchor.	4 / 5
Distinctiveness Conflict Risk	'Distinct from coding-variant tools' explicitly draws the boundary; the non-coding/regulatory niche is clear with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-regulatory-variant-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.