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

73%

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 ./plugin/skills/tooluniverse-variant-functional-annotation/SKILL.md

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 concrete tool calls, thresholds, and fallback chains. The main weakness is conciseness: the reasoning framework over-explains basic genetics concepts Claude already knows, and some long inline material (report template, annotator lists) would benefit from extraction into reference files.

Suggestions

Trim the 'Pathogenicity Reasoning Framework' to the actionable thresholds and decision rules, removing explanatory prose about what conservation and population frequency mean in general.

Move the full synthesis report template and the per-variant-type annotator string lists into a reference file (e.g. references/report-template.md) and link to it from SKILL.md.

Add an explicit validation/sanity-check step after synthesis (e.g. confirm all populated report fields, flag phases with no data) to serve as a workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tool names and thresholds, but the 'Pathogenicity Reasoning Framework' explains genetics concepts Claude already knows (e.g. 'If the residue has been maintained across vertebrates... mutation is likely to disrupt function') that could be trimmed without losing the valuable cutoffs.	3 / 5
Actionability	Gives concrete tool calls with parameters (e.g. `gnomad_get_variant` with 'chrom-pos-ref-alt' hg38 format, `OpenCRAVAT_annotate_variant` with specific annotator strings, `FAVOR_annotate_variant(variant="19-44908822-C-T")`), but presents them as prose rather than copy-paste executable code blocks.	4 / 5
Workflow Clarity	A clearly sequenced multi-phase pipeline (Phase 0→1→2→3→3b→4→5→Synthesis) with an ASCII diagram and explicit fallback chains for error recovery; this is a read-only annotation skill so the destructive-operation validation cap does not apply, but explicit output-validation checkpoints are absent.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled sections and phases with no nested references (no bundle files exist), but the ~230-line body keeps material inline — e.g. the full synthesis report template and annotator string lists — that could live in separate reference files.	4 / 5
	Total	15 / 20 Passed

Description

80%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 concrete data sources and gives explicit trigger guidance in third person. It would benefit from a few more natural user-facing trigger phrases to push completeness and trigger-term quality to the top anchor.

Suggestions

Add concrete user-style trigger phrases to the 'Use for' clause (e.g., 'Use when a user asks to annotate a variant, requests gnomAD frequency, or asks about the functional impact of a missense change').

Mention accepted input notations (HGVS, rsID, gene+protein change) in the description so users searching by those terms match this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete data sources/actions — 'ProtVar structural/functional context, ClinVar clinical classifications, gnomAD population frequencies, CADD deleteriousness, ClinGen gene-disease validity, plus FAVOR one-call comprehensive GRCh38 annotation' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers 'what' (functional annotation combining the listed sources) and 'when' via the 'Use for...' clause; both are present, but the 'when' could be more specific with concrete trigger phrases, so it sits just below the top anchor.	4 / 5
Trigger Term Quality	Good keyword coverage with natural phrases ('variant annotation pipelines, missense effect prediction, protein-level variant interpretation'), but a few common user variations (e.g. 'annotate my variant', 'is this variant pathogenic', rsID/HGVS mentions) are missing.	4 / 5
Distinctiveness Conflict Risk	The niche (protein-level functional annotation) is clearly scoped and distinct from full ACMG interpretation, but the mention of ClinVar/ClinGen creates minor overlap risk with the closely related variant-interpretation skill.	4 / 5
	Total	17 / 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-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.