tooluniverse-variant-interpretation

Clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Use for VUS classification, pathogenicity assessment with cited criteria, structure-based variant impact (AlphaFold/PDB), non-coding/regulatory variant effect prediction with sequence deep-learning models (AlphaGenome, Enformer, Borzoi, ChromBPNet, Evo 2), and producing clinical-grade variant reports for return of results or molecular tumor boards. Use this whenever a user asks about a variant's significance, an intronic/promoter/enhancer/UTR non-coding variant's functional impact, or needs ACMG classification — even if they don't say "ACMG".

Quality

89%

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

78%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 a strong, highly actionable clinical workflow with executable code and concrete tool guidance. Its main weaknesses are inlined reference-grade content that bloats the file and references to bundle files that are not actually present.

Suggestions

Create the referenced bundle files (ACMG_CLASSIFICATION.md, CODE_PATTERNS.md, CHECKLIST.md, EXAMPLES.md, TOOLS_REFERENCE.md) or remove the references, since none currently exist in the skill directory.

Move the inlined ACMG Bayesian algorithm, gene-specific frequency thresholds, predictor-weighting, and conflict-handling sections into ACMG_CLASSIFICATION.md to slim SKILL.md into a true overview.

Tighten the Phase 2.5 regulatory-context explanatory prose to tool/parameter essentials, trusting Claude's understanding of deep-learning variant-effect models.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no basic concept explanations), but the regulatory-context prose and predictor-weighting/conflict-handling sections add explanatory padding that could be trimmed or moved to reference files.	4 / 5
Actionability	Highly actionable: concrete tool names with parameters and return shapes throughout, plus copy-paste-ready executable Python (classify_acmg, ESM_explain_variant_mechanism) covering common cases.	5 / 5
Workflow Clarity	A clear six-phase sequence with explicit checkpoints ('LOOK UP, DON'T GUESS', Phase 2.9 short-circuit, tool-failure fallbacks), though per-phase validate-then-proceed gates are less explicit than the top anchor.	4 / 5
Progressive Disclosure	References to CODE_PATTERNS.md, ACMG_CLASSIFICATION.md, CHECKLIST.md, EXAMPLES.md, TOOLS_REFERENCE.md are well-signaled, but those files do not exist in the bundle, and substantial reference-grade content (full ACMG algorithm, gene thresholds, predictor weighting) is inlined in SKILL.md rather than split out.	3 / 5
	Total	16 / 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 exemplary: third-person voice, comprehensive concrete actions, explicit trigger guidance with natural user phrasing, and a clearly distinct clinical variant-interpretation niche. It even anticipates users who won't say 'ACMG'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'VUS classification', 'pathogenicity assessment with cited criteria', 'structure-based variant impact (AlphaFold/PDB)', 'non-coding/regulatory variant effect prediction', 'producing clinical-grade variant reports' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly states both what ('Clinical variant interpretation from raw variant calls to ACMG-classified recommendations...') and when ('Use this whenever a user asks about a variant's significance...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including 'variant's significance', 'ACMG classification', 'VUS', 'intronic/promoter/enhancer/UTR non-coding variant', 'functional impact', plus explicit guidance to trigger even when users don't say 'ACMG'.	5 / 5
Distinctiveness Conflict Risk	Clear clinical-genomics niche anchored by specific terms (ACMG, VUS, AlphaFold, AlphaGenome, molecular tumor boards); minimal overlap risk with other skills.	5 / 5
	Total	20 / 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-variant-interpretation/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.