CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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, variant-notation conversion (SPDI/HGVS/VCF/rsID interconversion, ALFA per-ancestry allele frequencies), European Variation Archive (EVA) lookups (per-study cohort variant data, RS-accession resolution), HGVS validation/normalization (Mutalyzer), gene-specific curated variants (LOVD), canonical cross-database allele IDs (ClinGen Allele Registry), automated ACMG/AMP classification (GeneBe), principal-transcript selection (APPRIS), Ensembl linkage disequilibrium (LD) for GWAS/fine-mapping, GRCh37/GRCh38 coordinate liftover and protein/cDNA-to-genomic mapping, and Ensembl ID utilities (stable-ID version history, cross-references, region/gene feature overlap, assembly/species metadata). Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants)...

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-variant-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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.

The body is exceptionally actionable, with concrete commands, verified tool behavior, explicit validation checkpoints and error-recovery loops, but it pays for that with poor token economy: concept explanations Claude already knows, triple-stated conventions, and ~400 lines of tool tables duplicated from the reference files. The reference bundle itself is well-structured and one level deep, but the SKILL.md has not actually moved the bulk detail out to it, and one cited file (QUICK_START.md) is missing.

Suggestions

Move the ToolUniverse tool tables (EVA, Variant Notation Conversion, Ensembl ID Utilities/Liftover/LD, Phenotype) into the existing reference files and keep only a one-row-per-tool 'when to use' summary with pointers in SKILL.md — the references already claim to hold the full tables, so the inline duplication is pure token cost.

State the coding-only-denominator rule once (e.g., in the PRIMARY SCRIPTS/variant_fraction.py row) and reference it elsewhere instead of repeating it in the CRITICAL section and again in Analysis Conventions; likewise drop background Claude already knows (LD definition, SpCas9 PAM orientation, VCF quality-filtering rationale).

Fix the dangling 'QUICK_START.md' reference — either add the file to the bundle or remove the pointer — since a cited-but-absent resource breaks navigation at exactly the point a reader needs it.

DimensionReasoningScore

Conciseness

The ~800-line body includes several sections of knowledge Claude already has — "LD measures non-random co-inheritance of alleles at different loci", CRISPR "PAM sequence (NGG for SpCas9) must lie 3' of the target", a generic VCF quality-filtering rationale, and definitions of SPDI/HGVS/VCF notation — and it is noticeably redundant: the coding-only-denominator rule appears three times (PRIMARY SCRIPTS table, the 'CRITICAL' section, and Analysis Conventions), and the notation-conversion parameter tables are inlined even though references/variant_notation_conversion.md already holds the 'full parameter tables'. This matches level 2 ('noticeably verbose; several unnecessary explanations or padded sections'); it is not level 1 because a large share of the content is genuinely valuable, non-obvious, live-verified tool knowledge.

2 / 5

Actionability

Copy-paste-ready bash invocations with concrete flags ("--workdir /tmp/hc_run --sample-name SAMPLE", "--pattern '*.xlsx' --header-rows 2"), python snippets with expected return values, named output keys to grep (SNP_COUNT_ALLELES, AVERAGE_PER_SAMPLE), tool call signatures with parameters and response shapes, and decision guides ('start from what you have, land on what you need'). This fully meets the level-5 anchor for executable, common-case-covering guidance.

5 / 5

Workflow Clarity

A clear ordered decision sequence exists (RULE ZERO pre-computed-results check → PRIMARY SCRIPTS → phase recipe), phases 1-7 are explicitly sequenced, and there are explicit validation checkpoints and feedback loops: scripts emit 'PLOIDY=<value> from the VCF header so you can confirm', a sanity check ('If your "synonymous fraction" is much lower than ~0.4 ... restrict to CODING and recompute'), retry-with-longer-timeout guidance for flaky endpoints, and the mandatory 'ALWAYS report all THREE proportions' checklist. Batch/destructive-adjacent operations (annotation batches, pipeline writes) do have verification steps, so no cap applies.

5 / 5

Progressive Disclosure

References are real, one level deep, and clearly signaled ('See references/vcf_filtering.md for all filter options'), and all cited scripts exist. However the body inlines hundreds of lines of ToolUniverse tool reference tables (EVA, notation conversion, Ensembl utilities, phenotype) that the skill itself says are fully documented in the reference files — content that clearly belongs in separate files is inline, matching level 3 ('content that should be separate is inline'). Additionally, 'QUICK_START.md' is cited under Additional Resources but is absent from the bundle, a dangling reference.

3 / 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 dense, highly specific description with an explicit 'Use for' trigger clause; it clearly communicates a specialized variant-analysis niche. Its main flaws are the truncated, narrow 'when' clause (ending in '...' and covering only a fraction of the stated capabilities) and the absence of a few common natural terms like SNP/SNV/indel/ClinVar and .vcf.

Suggestions

Fix the truncated trigger clause — the description currently ends '...Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants)...' with a dangling ellipsis; replace it with a complete 'Use when...' sentence.

Broaden the 'when' clause to match the breadth of the 'what' (e.g., 'Use for VCF parsing, variant classification and VAF filtering, SPDI/HGVS/rsID conversion, HGVS validation, ACMG classification, coordinate liftover, and LD/gene-level queries').

Add commonly used natural terms users would type — 'SNP', 'SNV', 'indel', 'ClinVar', '.vcf' — to strengthen trigger matching and distinctiveness against neighboring genomics skills.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions with concrete object nouns — "parsing, annotation, classification (synonymous, missense, frameshift, stop_gained), VAF filtering, coding vs non-coding categorization", "variant-notation conversion (SPDI/HGVS/VCF/rsID interconversion...)", "GRCh37/GRCh38 coordinate liftover", "stable-ID version history". This is comprehensive, specific coverage of the skill's capability surface, matching the level-5 anchor ('multiple specific concrete actions; comprehensive coverage') rather than level 4, which is for coverage with notable gaps.

5 / 5

Completeness

Both 'what' and 'when' are present: an extensive capability list followed by "Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants)". However the 'when' clause is literally truncated with a trailing "..." and names only two of the many capabilities the 'what' enumerates (nothing about liftover, LD, LOVD, HGVS validation, etc.), so the trigger guidance is less explicit and narrower than the level-5 anchor demands.

4 / 5

Trigger Term Quality

Strong domain keywords users would naturally say — "VCF", "variant", "missense", "HGVS", "liftover", "GWAS", "Ensembl", "ClinVar"-adjacent terms — but a few common natural terms are missing: "SNP", "SNV/indel", "ClinVar" itself, and the ".vcf" file extension. Coverage is good but not the comprehensive synonym-plus-extension coverage of the level-5 anchor (compare 'PDF files, PDFs, forms, .pdf').

4 / 5

Distinctiveness Conflict Risk

The niche is largely distinct — tool names like Mutalyzer, LOVD, GeneBe, APPRIS, EVA, and SPDI/ALFA terminology are strong discriminators. But the broad opener "VCF and variant analysis — parsing, annotation, classification" plus "Ensembl linkage disequilibrium (LD) for GWAS/fine-mapping" and "Ensembl ID utilities" extend into territory plausibly claimed by sibling genomics/bioinformatics skills, leaving minor overlap risk consistent with the level-4 anchor rather than the minimal-conflict level-5 anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (809 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

Reviewed

Table of Contents

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.