Name: tooluniverse-variant-functional-annotation
Rating: 68 (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

81%

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

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

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-constructed operational skill: clear phase workflow, concrete tool parameters, domain-specific thresholds, and thoughtful fallback chains. It falls short of top marks mainly on missing explicit validation gating, absent full example invocations, and an all-inline structure that could offload per-phase API detail to reference files.

Suggestions

Add one complete example call with a trimmed sample result for the core tools (e.g., ProtVar_map_variant and gnomad_get_variant) so guidance is copy-paste ready, lifting actionability.

Insert explicit validation checkpoints between phases (e.g., verify Phase 0 normalization resolved to a single canonical transcript before proceeding, and confirm each phase returned data before synthesis) to strengthen workflow clarity.

Move per-phase tool parameter detail into a one-level-deep reference file (e.g., references/tool-reference.md) and keep SKILL.md as the workflow overview, improving progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-generic specifics (CADD PHRED ≥ 30, gnomAD AF < 0.001, REVEL ≥ 0.75, ClinVar star semantics, verbatim annotator strings) that earn their tokens; only the generic "LOOK UP, DON'T GUESS" / "COMPUTE, DON'T DESCRIBE" sections read as trimmable padding, fitting the efficient-with-minor-overexplanation anchor.	4 / 5
Actionability	Tool calls are specified with exact parameter names and formats (e.g., variant_id as "chrom-pos-ref-alt (hg38, no 'chr' prefix)", FAVOR_annotate_variant(variant="19-44908822-C-T"), verbatim annotator lists) plus fallback chains, but there is no complete copy-paste example call and result per tool, so it stops short of fully-executable guidance.	4 / 5
Workflow Clarity	The numbered Phase 0–5 sequence, ASCII workflow overview, and explicit per-tool fallback chains give a clear sequence with error recovery, but validation checkpoints are mostly implicit (Phase 0 "confirm gene/transcript", the "Data Gaps" report section) rather than explicit gating steps, matching the most-checkpoints-present anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the single ~230-line SKILL.md is cleanly sectioned with no broken or buried references, giving good structure; however the per-phase API detail is a natural candidate for a one-level-deep reference split, so it is not the clear-overview-with-signaled-references anchor.	4 / 5
	Total	16 / 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 description: it enumerates six specific annotation capabilities and gives an explicit, concrete 'Use for' clause covering the main use cases. Its only weaknesses are a few missing natural trigger terms (pathogenicity, HGVS/rsID inputs) and residual overlap risk with the sibling variant-interpretation skill.

Dimension	Reasoning	Score
Specificity	"ProtVar structural/functional context, ClinVar clinical classifications, gnomAD population frequencies, CADD deleteriousness, ClinGen gene-disease validity, plus FAVOR one-call comprehensive GRCh38 annotation" names six concrete data sources with the capability drawn from each, matching the comprehensive-coverage anchor rather than the minor-gaps anchor.	5 / 5
Completeness	It explicitly answers both what ("Functional annotation of protein variants — …") and when ("Use for variant annotation pipelines, missense effect prediction, and protein-level variant interpretation with functional context") with concrete trigger phrases, so it is not the anchor-4 case of an only-adequate 'when' clause.	5 / 5
Trigger Term Quality	"variant annotation pipelines", "missense effect prediction", and "protein-level variant interpretation" are natural user phrasings, but common terms like "pathogenic", "is this variant harmful", or input notations (HGVS, rsID) are missing — good coverage with a few natural terms absent.	4 / 5
Distinctiveness Conflict Risk	The protein-level functional-evidence niche with named tools (ProtVar, FAVOR) is mostly distinct, but a closely related sibling skill (tooluniverse-variant-interpretation) covers overlapping ClinVar/CADD/gnomAD territory, keeping overlap risk above minimal.	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: 164aaf1

Reviewed: 6 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.