tooluniverse-structural-variant-analysis

Comprehensive structural variant (SV) analysis skill for clinical genomics. Classifies SVs (deletions, duplications, inversions, translocations), assesses pathogenicity using ACMG-adapted criteria, evaluates gene disruption and dosage sensitivity, and provides clinical interpretation with evidence grading. Use when analyzing CNVs, large deletions/duplications, chromosomal rearrangements, or any structural variants requiring clinical interpretation.

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 ./skills/bio/tooluniverse-structural-variant-analysis/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, well-sequenced clinical-genomics workflow with valuable ACMG/dosage reference material, but it is bloated and monolithic: redundant diagrams, pseudocode stubs with disclaimers, no explicit validation gates, and bundle-file references that do not exist.

Suggestions

Trim redundancy and pseudocode: remove the ASCII workflow box that duplicates the Phase Details headings, drop the score-visualization bars, and either make the Python examples executable or move them to a scripts/ file — keep SKILL.md focused on the decision logic and ACMG/dosage tables.

Apply progressive disclosure: split the worked 17q21.31 example, the full ACMG criteria tables, and the code implementations into references/ files (and create the referenced EXAMPLES.md/README.md or remove the dead 'See Also' links), leaving SKILL.md as a concise overview with one-level-deep links.

Add explicit validation checkpoints to the workflow — e.g., a gate after gene-content/dosage analysis confirming ClinGen scores were retrieved for every contained gene before scoring, and a reconcile step when population-frequency and ClinVar evidence conflict.

Dimension	Reasoning	Score
Conciseness	The body is ~1350 lines with real padding — an ASCII workflow box that duplicates the phase headings, score-breakdown visualization bars, and Python stubs flagged 'This is pseudocode - actual implementation depends on available tools'. Not 3 because it is far from lean; not 1 because the bulk is domain-specific reference material (ACMG SV codes, dosage scoring) rather than generic concepts Claude already knows.	2 / 3
Actionability	Concrete elements exist (named tool signatures like tu.tools.ClinGen_search_dosage_sensitivity(gene=...), ACMG criteria tables, report templates), but the code blocks are explicitly pseudocode with disclaimers and commented-out logic ('# inheritance_pattern = parse_inheritance(details)', 'May need to use myvariant'). Not 3 because the examples are not copy-paste executable; not 1 because the tables and tool calls are specific and instructive.	2 / 3
Workflow Clarity	The 7 phases are clearly sequenced with goals and a 'Quantified Minimums' checklist, but validation/feedback checkpoints are implicit (evidence grading, completeness table) rather than explicit validate->fix->retry gates. Not 3 because explicit validation steps and error-recovery loops are absent; not 1 because the sequence and per-phase structure are unambiguous.	2 / 3
Progressive Disclosure	Section organization is clear, but the document is a monolithic 1350-line wall with examples, full code, and report templates all kept inline, and 'See Also' references EXAMPLES.md/README.md that are not present in any bundle directory. Not 3 because nothing is actually split into bundle files; not 1 because references are one-level and sections are well organized.	2 / 3
	Total	8 / 12 Passed

Description

100%

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, third-person description that names concrete capabilities, provides explicit natural-language triggers, and occupies a distinct niche. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Classifies SVs (deletions, duplications, inversions, translocations), assesses pathogenicity using ACMG-adapted criteria, evaluates gene disruption and dosage sensitivity, and provides clinical interpretation with evidence grading' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (classify/assess/evaluate/interpret SVs) and when via an explicit 'Use when...' clause. Not 2 because the when-trigger is explicit rather than implied.	3 / 3
Trigger Term Quality	'Use when analyzing CNVs, large deletions/duplications, chromosomal rearrangements, or any structural variants requiring clinical interpretation' covers the natural terms a genomics user would actually say. Not below 3 because common variations (CNVs, deletions/duplications, rearrangements) are all present.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear clinical-genomics niche (SV/CNV pathogenicity) with distinct triggers and an explicit handoff to a separate SNV skill, so it is unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1357 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-structural-variant-analysis/SKILL.md
Commit: df37802

Reviewed: 2 days 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.