tooluniverse-variant-interpretation

Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability.

Quality

82%

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

Quality

Content

65%

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

The body is highly actionable with concrete tool calls and thresholds, but it is verbose (duplicate frontmatter, motivation section, stale year), lacks explicit validation feedback loops, and references bundle files that are absent. Organization is strong but disclosure and verification are not realized.

Suggestions

Remove the duplicate YAML frontmatter block (lines 6-9) and trim the 'Problem This Skill Solves' motivation section and ASCII workflow box to reduce token waste.

Add an explicit validate-then-proceed checkpoint (confirm Quantified Minimums are met before ACMG classification) and create the referenced CHECKLIST.md so the verification step is real rather than a dead link.

Either create CHECKLIST.md, EXAMPLES.md, and TOOLS_REFERENCE.md or remove the broken 'See Also' links; consider moving the large inline tool reference into TOOLS_REFERENCE.md for genuine one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is concrete and mostly efficient, but carries unnecessary weight: a duplicated YAML frontmatter block (lines 6-9), a motivation-heavy 'Problem This Skill Solves' section, a large ASCII workflow box, minor explanatory prose ('SpliceAI is the gold standard'), and a time-sensitive hardcoded year ('{GENE} genetics 2024'). Not a 3 because not every token earns its place; not a 1 because it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	Provides copy-paste-ready Python functions with real tool names and parameters (e.g. ClinGen_search_gene_validity, SpliceAI_predict_splice), plus specific threshold tables and ACMG code mappings, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Phases are clearly sequenced (1 through 6 plus 2.5/4.5) with a 'Quantified Minimums' gate, but there are no explicit validate-then-retry feedback loops and the referenced verification artifact (CHECKLIST.md) does not exist; for a multi-source batch aggregation this caps the score at 2 per the batch-operation guideline.	2 / 3
Progressive Disclosure	Sections are well-organized with headers, but the file is a monolithic 1118-line body and the three 'See Also' references (CHECKLIST.md, EXAMPLES.md, TOOLS_REFERENCE.md) point to files that do not exist in references/scripts/assets, leaving navigation broken.	2 / 3
	Total	9 / 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.

The description is specific, uses natural trigger terms, answers both what and when with an explicit 'Use when' clause, and occupies a distinctive niche. Voice is appropriately third person with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB' and 'Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states both what it does and when to use it via a 'Use when...' clause naming four trigger scenarios, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Covers natural domain terms a user would say — 'interpreting genetic variants', 'variants of uncertain significance (VUS)', 'ACMG variant classification', 'translating variant calls to clinical actionability' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (ACMG clinical variant interpretation with structural analysis) with distinct triggers unlikely to fire for unrelated skills.	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 (1119 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-variant-interpretation/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.