CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-acmg-variant-classification

Systematic ACMG/AMP germline variant classification with all 28 criteria (PVS1, PS1-4, PM1-6, PP1-5, BA1, BS1-4, BP1-7) for clinical significance. Produces 5-tier verdict (Pathogenic / Likely Pathogenic / VUS / Likely Benign / Benign) with cited evidence per criterion. Use for variant interpretation, VUS resolution, and pathogenicity assessment. Combines ClinVar, gnomAD, computational predictors, and gene-mechanism context.

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable skill body with a clear phased workflow and concrete tool usage throughout. Splitting the large tool-reference table and classification rules into reference files and replacing placeholder arguments would lift it to the top anchors.

Suggestions

Move the 18-row Tool Parameter Reference table into a references/ file (e.g. TOOLS.md) and link to it from the body to reduce top-level token load.

Replace placeholder arguments like variant_id="..." and hgvs_notation="..." with concrete example values so the code blocks are fully copy-paste ready.

Tighten or remove the generic 'LOOK UP, DON'T GUESS' section, which restates general behavior rather than ACMG-specific guidance.

DimensionReasoningScore

Conciseness

The body is mostly dense and actionable domain guidance rather than re-explained basics, with only minor generic padding (e.g. the 'LOOK UP, DON'T GUESS' section) that could be trimmed.

4 / 5

Actionability

Each phase ships concrete tool calls with real parameters, but several examples leave placeholder values such as variant_id="..." and hgvs_notation="...", which are minor gaps from copy-paste readiness.

4 / 5

Workflow Clarity

A clear Phase 0 through Phase 6 sequence plus an explicit Classification Algorithm with combination rules, with Phase 0 serving as a validation checkpoint; feedback loops are present but not uniformly explicit across phases.

4 / 5

Progressive Disclosure

Well-organized section headers structure the ~240-line body clearly, but all content is inlined with no bundle files, so the tool-reference table and classification rules could be split out for lighter top-level loading.

4 / 5

Total

16

/

20

Passed

Description

92%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 both capability and trigger use cases with concrete domain terms. Slightly richer natural-language trigger phrasing would push trigger term quality to the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Systematic ACMG/AMP germline variant classification', 'Produces 5-tier verdict...with cited evidence per criterion', and 'Combines ClinVar, gnomAD, computational predictors, and gene-mechanism context' — giving comprehensive coverage rather than a couple of generic actions.

5 / 5

Completeness

Explicitly answers 'what' (classification producing a 5-tier verdict with cited evidence) and 'when' via a concrete 'Use for variant interpretation, VUS resolution, and pathogenicity assessment' clause.

5 / 5

Trigger Term Quality

Includes natural terms ('variant interpretation, VUS resolution, and pathogenicity assessment') alongside the technical criteria names, but misses common user phrasings such as 'is this variant pathogenic' or 'classify this variant'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (ACMG/AMP germline variant classification) with highly specific triggers, making conflict with unrelated skills minimal.

5 / 5

Total

19

/

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.