CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

82%

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-structural-variant-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 and assumes Claude's competence with concrete tool guidance, but it lacks explicit validation feedback loops for a clinical-call workflow and references four detail files that are not present in the bundle.

Suggestions

Add explicit validation/checkpoint steps in Phases 4-7 (e.g., 'if ClinGen returns no HI/TS score, fall back to OMIM inheritance as weaker evidence and re-score') to create a validate→fix→retry loop and lift workflow clarity above the batch-operation cap of 3.

Ship the referenced bundle files (CLASSIFICATION_GUIDE.md, ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, EXAMPLES.md) or inline their essential content so the one-level-deep references actually resolve.

De-duplicate the dosage-sensitivity reasoning between 'SV Pathogenicity Reasoning (Start Here)' and Phase 3, and collapse the Phase 5 overview with its detailed mapping, to tighten conciseness toward a 5.

DimensionReasoningScore

Conciseness

Mostly efficient and trusts Claude's knowledge (e.g., 'The LLM knows the ACMG criteria codes and combination rules'), but dosage-sensitivity reasoning is repeated between the 'Start Here' section and Phase 3, and the Phase 5 scoring overview is restated in detail — minor trimming possible.

4 / 5

Actionability

Concrete tool calls per phase with specific thresholds ('>=70% reciprocal overlap', 'ClinGen HI score 3', 'pLI >= 0.9', '>=1% frequency → BA1') and an explicit 0-10 score-to-tier mapping, but the actual implementation pseudocode is deferred to ANALYSIS_PROCEDURES.md, leaving a minor gap.

4 / 5

Workflow Clarity

The 7-phase sequence is clearly laid out, but for a batch/clinical-call workflow there are no explicit validation checkpoints or validate→fix→retry feedback loops before the final classification, which per the rubric caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Structure is well organized with a 'Reference Files' section and one-level-deep pointers, but the referenced files (CLASSIFICATION_GUIDE.md, ANALYSIS_PROCEDURES.md, REPORT_TEMPLATE.md, EXAMPLES.md) are cited yet not present in the bundle, so navigation does not resolve.

3 / 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 actions, natural trigger terms, and an explicit 'Use for...' clause that answers both what and when. It carves out a distinct clinical-genomics niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across all SV types — 'Applies ACMG-adapted criteria with ClinGen HI/TS dosage scores, gnomAD frequencies, and ClinVar evidence' and 'Produces 5-tier classification with explicit per-criterion evidence' — giving comprehensive coverage of capabilities.

5 / 5

Completeness

Both 'what' (SV clinical interpretation, applies ACMG-adapted criteria, produces 5-tier classification) and 'when' ('Use for clinical genomics SV review, dosage-sensitivity assessment, breakpoint analysis, and CNV pathogenicity calls') are explicitly and concretely answered.

5 / 5

Trigger Term Quality

Natural user-facing terms are well covered with synonyms — 'structural variant', 'deletions, duplications, inversions, translocations', 'CNV pathogenicity calls', 'clinical genomics SV review', and 'dosage-sensitivity assessment'.

5 / 5

Distinctiveness Conflict Risk

A clearly defined clinical-genomics SV niche with distinct triggers; the body further reduces conflict risk by redirecting SNVs and small indels to a sibling skill, minimizing wrong-skill triggering.

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.