tooluniverse-structural-variant-analysis

Structural variant (SV) clinical interpretation: deletions, duplications, inversions, translocations, complex rearrangements. Applies ACMG-adapted criteria with ClinGen HI/TS dosage scores, gnomAD frequencies, and ClinVar evidence. Produces 5-tier classification with explicit per-criterion evidence. Use for clinical genomics SV review, dosage-sensitivity assessment, breakpoint analysis, and CNV pathogenicity calls. Gene-dosage-driven reasoning.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-structural-variant-analysis/SKILL.md

Quality

Content

53%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 clearly sequenced, well-structured clinical workflow with good progressive disclosure signaling, but it leans on reasoning prose over executable code and delegates validation/scoring details to reference files that are not present in the bundle.

Suggestions

Add at least one executable Python snippet (e.g. a reciprocal-overlap or weighted-score calculation) to make the COMPUTE, DON'T DESCRIBE directive actionable rather than aspirational.

Inline a brief verification/checklist step in Phase 7 (e.g. confirm every applied ACMG code is backed by a tool-retrieved value) so the scoring workflow has an explicit validation checkpoint.

Either include the referenced bundle files (CLASSIFICATION_GUIDE.md, ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, EXAMPLES.md) or remove the references, since they currently point to files that do not exist.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the SV Pathogenicity Reasoning section restates dosage-sensitivity concepts (e.g. 'A deletion of a dosage-insensitive gene in a gene-dense region may be benign') that echo the domain knowledge rather than adding tool-specific procedure, and the workflow could be tightened.	3 / 5
Actionability	Concrete tool names and thresholds are given, but Phases defer details to reference files and the COMPUTE section prescribes Python without any executable example, so guidance is partly specific yet incomplete and lacks copy-paste-ready code.	3 / 5
Workflow Clarity	A clear 7-phase sequence with per-phase goals is present, but validation checkpoints are largely implicit and Phase 7 ACMG scoring is delegated to CLASSIFICATION_GUIDE.md without inline verification; per the batch/destructive cap guidance, missing explicit validation caps this at 3.	3 / 5
Progressive Disclosure	The body is a well-organized overview that signals one-level-deep references (CLASSIFICATION_GUIDE.md, ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, EXAMPLES.md) at the right points. However none of these bundle files are actually present in the directory, so referenced paths cannot be verified, holding it just below a 5.	4 / 5
	Total	13 / 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 what the skill does and when to use it with natural trigger phrases. Minor overlap risk with a sibling variant-interpretation skill is mitigated by the body's explicit scope boundary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and a specific output ('Produces 5-tier classification with explicit per-criterion evidence') grounded in named frameworks (ACMG, ClinGen HI/TS, gnomAD, ClinVar), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (SV clinical interpretation applying ACMG-adapted criteria) and when ('Use for clinical genomics SV review, dosage-sensitivity assessment, breakpoint analysis, and CNV pathogenicity calls'), matching the concrete-trigger-phrases anchor.	5 / 5
Trigger Term Quality	Covers natural phrases users would say ('is this deletion/duplication pathogenic?', 'CNV pathogenicity calls', 'breakpoint analysis', 'dosage-sensitivity assessment') plus technical synonyms, giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The SV/CNV dosage niche is distinct and the body adds a 'When NOT to Use' boundary to tooluniverse-variant-interpretation, but the description alone overlaps slightly with a sibling variant-interpretation skill, so it is just shy of the minimal-conflict anchor.	4 / 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: plugin/skills/tooluniverse-structural-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.