Name: tooluniverse-variant-functional-annotation
Rating: 65.60000000000001 (1 reviews)
Author: mims-harvard

tooluniverse-variant-functional-annotation

Functional annotation of protein variants — ProtVar structural/functional context, ClinVar clinical classifications, gnomAD population frequencies, CADD deleteriousness, ClinGen gene-disease validity, plus FAVOR one-call comprehensive GRCh38 annotation. Use for variant annotation pipelines, missense effect prediction, and protein-level variant interpretation with functional context.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-variant-functional-annotation/SKILL.md

The canonical home for this skill is tooluniverse-variant-functional-annotation in mims-harvard/ToolUniverse

Quality

Content

67%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 annotation workflow with clear phasing and robust fallback chains. The main weaknesses are conceptual prose that restates known genetics reasoning and the absence of executable code examples or externalized reference material.

Suggestions

Trim the Pathogenicity Reasoning Framework and KEY PRINCIPLES to operational decision rules, removing explanation of basic conservation and frequency concepts Claude already knows.

Add at least one copy-paste-ready example showing a full annotation call sequence and result handling for a representative variant.

Move the detailed per-tool parameter reference and annotator string recipes into a separate references file, keeping SKILL.md as a lean overview pointing to it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with well-organized tool-call reference, but the prose Pathogenicity Reasoning Framework and KEY PRINCIPLES re-explain concepts (conservation, population frequency logic) Claude already knows, adding length without new operational detail.	3 / 5
Actionability	Provides concrete tool names with parameter signatures and formats (e.g., gnomad_get_variant 'chrom-pos-ref-alt' hg38, CADD without 'chr' prefix), but offers no executable code examples and the report template is structural pseudocode.	4 / 5
Workflow Clarity	A clear phased sequence (Phase 0–5 plus Synthesis) with explicit fallback chains for each tool failure; checkpoints are implicit via T1–T4 grading rather than explicit validate-and-retry steps, so it sits just below 5.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and a self-contained scope; no bundle files exist to split out, and the one-level layout navigates well, though some API-reference detail could be externalized to a reference file.	4 / 5
	Total	15 / 20 Passed

Description

88%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 names six concrete data sources and gives explicit use-when guidance in third-person voice. Trigger phrasing is slightly jargon-heavy and overlaps with closely related variant skills.

Suggestions

Add one or two natural user phrases (e.g., 'is this variant pathogenic', 'annotate rsID/HGVS') to broaden trigger coverage beyond technical terminology.

Sharpen distinctiveness from tooluniverse-variant-interpretation within the description itself (e.g., 'protein-level functional context only; not full ACMG classification').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — ProtVar structural/functional context, ClinVar classifications, gnomAD frequencies, CADD scoring, ClinGen validity, and FAVOR one-call annotation — giving comprehensive coverage of actions.	5 / 5
Completeness	Explicitly answers both what (functional annotation combining six named sources) and when via the 'Use for variant annotation pipelines, missense effect prediction, and protein-level variant interpretation' clause with concrete triggers.	5 / 5
Trigger Term Quality	Strong domain keywords ('variant annotation pipelines', 'missense effect prediction', 'protein-level variant interpretation') but leans technical and omits natural phrasings users would say (e.g., 'rsID', 'HGVS', 'is this mutation harmful').	4 / 5
Distinctiveness Conflict Risk	Occupies a clear protein-level functional-evidence niche distinct from general variant interpretation, but the broad term 'variant annotation' creates some overlap risk with sibling tooluniverse-variant skills.	4 / 5
	Total	18 / 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: plugins/tooluniverse/skills/tooluniverse-variant-functional-annotation/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.