tooluniverse-variant-analysis

VCF and variant analysis — parsing, annotation, classification (synonymous, missense, frameshift, stop_gained), VAF filtering, coding vs non-coding categorization, multi-condition variant comparison. Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants), and per-sample mutation profiling.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-variant-analysis/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 detailed, highly actionable skill body anchored by concrete bundled-script invocations and a clear check-first workflow. Its main weaknesses are redundancy (the coding-denominator rule stated four times), some generic biology padding, a broken QUICK_START.md reference, and python examples that lean on APIs not present in the bundle.

Suggestions

Consolidate the coding-denominator convention into one location and reference it elsewhere instead of restating it in the PRIMARY SCRIPTS table, CRITICAL section, 'Proportion classified as benign', and Analysis Conventions.

Remove or relocate the CRISPR sgRNA Design Reasoning section — its PAM/off-target basics are concepts Claude already knows and dilute the skill's focus.

Fix the broken QUICK_START.md reference (line 467) by either creating the file or removing the pointer.

Dimension	Reasoning	Score
Conciseness	Most content is valuable domain gotchas Claude would not know, but the coding-denominator convention is restated in four places (PRIMARY SCRIPTS table, CRITICAL section, 'Proportion classified as benign', and Analysis Conventions) and the CRISPR sgRNA section explains basic biology Claude already knows (NGG PAM, off-target risk), so it could be tightened.	3 / 5
Actionability	Concrete, copy-paste-ready bash invocations with real flags and paths dominate the operational sections, but several python_implementation examples (variant_analysis_pipeline, answer_vaf_mutation_fraction, FilterCriteria) reference APIs not present in the bundled scripts, leaving minor gaps.	4 / 5
Workflow Clarity	A clear top-of-file operational sequence (RULE ZERO check-first → PRIMARY SCRIPTS → concrete invocations) with sanity checkpoints (e.g. 'if your synonymous fraction is much lower than ~0.4, restrict to CODING'), though there is no formal validate→fix→retry loop for the batch re-running operations.	4 / 5
Progressive Disclosure	Good structure with well-signaled, one-level-deep references to four real reference files and the scripts directory, but QUICK_START.md is referenced and does not exist in the bundle, and substantial inline content (repeated denominator conventions, tool reference tables) could be split out.	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, third-person description that comprehensively lists concrete capabilities and pairs them with an explicit 'Use for' trigger clause. It is held back from a perfect profile only by a jargon-heavy, slightly implementation-flavored trigger phrase that blurs naturalness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'parsing, annotation, classification (synonymous, missense, frameshift, stop_gained), VAF filtering, coding vs non-coding categorization, multi-condition variant comparison' plus 'variant fraction calculations' and 'per-sample mutation profiling' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated analysis actions) and 'when' via a concrete 'Use for VCF parsing, variant fraction calculations ... and per-sample mutation profiling' trigger clause.	5 / 5
Trigger Term Quality	Strong keyword coverage (VCF, variant, VAF, synonymous/missense/frameshift) that a bioinformatics user would naturally say, but the 'Use for' clause is jargon-laden and leaks an implementation gotcha ('denominator = coding subset only, NOT all variants') that reads as an internal note rather than a natural trigger, and it lacks the .vcf extension.	4 / 5
Distinctiveness Conflict Risk	The niche is largely distinct — VAF filtering, coding-vs-non-coding categorization, and per-sample mutation profiling are specific triggers — but the broad lead 'VCF and variant analysis' could overlap with other bioinformatics/variant skills, leaving minor conflict risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (503 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-variant-analysis/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.