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.

72

Quality

88%

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

77%

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

A highly actionable, well-sequenced classification workflow with concrete tool calls, explicit thresholds, and a clear output template. Its main weaknesses are length-driven conciseness and the absence of any progressive disclosure via bundle files despite being a long monolithic document.

Suggestions

Tighten the conceptual prose in each phase (e.g., 'Population AF is among the strongest evidence in either direction') and merge the KEY PRINCIPLES list into the phase guidance where they are already implied, cutting tokens without losing the specific thresholds.

Move the Tool Parameter Reference table and the Common Patterns walkthroughs into references/ files (e.g., TOOLS.md and PATTERNS.md) and link them one level deep from SKILL.md to improve progressive disclosure and reduce the monolithic body.

Add an explicit per-phase validation micro-checklist (e.g., 'confirm MANE transcript match before proceeding') so the validation feedback loop is as visible as the Phase 0 framing.

DimensionReasoningScore

Conciseness

Mostly efficient and packed with specific thresholds (REVEL >= 0.7, PP1_Strong at >= 7 meioses, pLI >= 0.9), but at ~240 lines some conceptual framing ('Population AF is among the strongest evidence') and the restated KEY PRINCIPLES list could be tightened.

2 / 3

Actionability

Every phase ships concrete tool invocations with parameters, a full tool-parameter table, explicit classification combination rules, a copy-ready output template, and worked end-to-end patterns.

3 / 3

Workflow Clarity

The seven phases are clearly sequenced with Phase 0 as an explicit validation-first checkpoint, plus short-circuit gating (BA1) and 'note the gap and continue' recovery guidance; the read-only analysis task does not require destructive feedback loops.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single well-sectioned 240-line document, but nothing is split out — the tool reference table and worked patterns are inline content that could live in separate reference files.

2 / 3

Total

10

/

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 concisely states concrete capabilities, explicit use-when triggers, and natural clinical keywords within a clearly distinctive niche. It answers both what the skill does and when to invoke it without padding.

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' — rather than vague language.

3 / 3

Completeness

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

3 / 3

Trigger Term Quality

Includes natural terms a clinician would actually say — 'variant interpretation', 'VUS resolution', 'pathogenicity assessment', and 'ACMG/AMP' — with good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

The ACMG/AMP germline variant-classification niche is highly specific with distinct triggers, making conflict with unrelated skills unlikely.

3 / 3

Total

12

/

12

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.