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

82%

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

Quality

Content

65%

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

The body is highly actionable with executable scripts and concrete gotchas, but is verbose — duplicating the coding-denominator convention and explaining domain concepts Claude already knows — and bundles much detail inline rather than deferring to the reference files it already ships.

Suggestions

Consolidate the coding-denominator/coding-subset guidance into a single section; it is currently repeated in PRIMARY SCRIPTS, the CRITICAL block, the variant_fraction script description, and Analysis Conventions.

Trim tutorial-style concept explanations (e.g. the 2x-depth reliability paragraph, CRISPR PAM basics) to the non-obvious gotchas only, since Claude already knows VCF filtering fundamentals.

Move the detailed core-capability tables, workflow phases, and tool reference into the existing reference files, keeping SKILL.md as a lean overview that points to them.

Dimension	Reasoning	Score
Conciseness	The body is efficient in places but explains concepts Claude already knows ("A variant called at 2x read depth is unreliable regardless of its QUAL score", CRISPR PAM basics) and repeats the coding-denominator point across four sections (PRIMARY SCRIPTS, CRITICAL, Analysis Conventions, variant_fraction description).	2 / 3
Actionability	Provides copy-paste-ready bash/python invocations with concrete flags, named scripts, output keys to grep ("SNP_COUNT_ALLELES", "AVERAGE_PER_SAMPLE"), and explicit right-vs-wrong command contrasts.	3 / 3
Workflow Clarity	Sequencing is present (RULE ZERO → PRIMARY SCRIPTS → invocations → output keys) with some checkpoints (PLOIDY emission, synonymous-fraction sanity ~0.4), but batch/destructive operations lack crisp validate→fix→retry loops and the workflow is scattered across overlapping sections.	2 / 3
Progressive Disclosure	References are real files signaled one level deep (mutation_classification_guide.md, vcf_filtering.md, annotation_guide.md, sv_cnv_analysis.md), but the SKILL.md itself is a ~500-line monolith with detail that could live in those references.	2 / 3
	Total	9 / 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.

The description is specific, third-person, and explicitly answers both what the skill does and when to use it, with natural trigger terms and a distinct niche. No meaningful weaknesses relative to the rubric anchors.

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" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what (full action list) and when via the explicit "Use for VCF parsing, variant fraction calculations ... and per-sample mutation profiling" clause, in third person.	3 / 3
Trigger Term Quality	Natural terms a user would say ("VCF", "variant analysis", "VAF filtering", "variant fraction calculations", "per-sample mutation profiling") with good coverage and no jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (VCF/variant analysis) with distinct, domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 7 hours 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.