CtrlK
BlogDocsLog inGet started
Tessl Logo

ngs-dna-somatic-variants

Run or plan tumor-normal, tumor-only, WGS, WES, or cancer-panel somatic variant workflows with pairing, contamination, panel-of-normals, purity, QC, and annotation checks.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 content is lean, actionable, and well-structured with concrete executable commands and clear validation cues. Its main gap is the absence of an explicit validate→fix→retry feedback loop and the lack of progressive-disclosure reference files for the larger command/output detail.

Suggestions

Add an explicit numbered execution sequence with a validate→fix→retry loop, e.g. run preflight → review install plan → fix missing resources → re-run with --require-resource-plan before proceeding.

Move the full flag/output-manifest detail into a references/ file (e.g. SOMATIC_RUNNER.md) and link to it from the body to improve progressive disclosure.

Add a short explicit verification step confirming pairing-table correctness before --execute, with a recovery path if pairs are missing or swapped.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence—it never explains what somatic variants are or how GATK/Mutect2 works—and every section (Essential Inputs, Route, Decision Points, Outputs) earns its place without padding.

5 / 5

Actionability

Provides two fully executable command blocks with concrete flags (the preflight and the Mutect2 runner) plus a concrete list of produced artifacts, covering the common tumor-normal/tumor-only cases in copy-paste-ready form.

5 / 5

Workflow Clarity

A clear route exists (confirm inputs → preflight → route → run → decision points → outputs) with checkpoints like pair-metadata verification and the advisory resource check, but it is organized topically rather than as a numbered sequence with an explicit validate→fix→retry feedback loop.

4 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is well organized with clear section headers and no nested references; it inlines some detail (full flag lists, output manifests) that could be split into reference files, leaving minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

75%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.

The description is specific and distinctive with strong natural trigger terms, but it omits an explicit "Use when..." clause, which caps its completeness. Adding concrete trigger guidance would round out the score.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user requests somatic/tumor variant calling, cancer-panel analysis, or tumor-normal pairing from FASTQ/BAM/CRAM."

Add common file-extension synonyms (FASTQ, BAM, CRAM, .vcf) to broaden trigger-term coverage.

Contrast with the germline skill inline (e.g. "not for inherited germline or family analysis") to sharpen distinctiveness in the description itself.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities—"tumor-normal, tumor-only, WGS, WES, or cancer-panel somatic variant workflows" plus "pairing, contamination, panel-of-normals, purity, QC, and annotation checks"—giving comprehensive coverage of the workflow's facets.

5 / 5

Completeness

Clearly states the "what" (run/plan somatic variant workflows with named checks) but lacks an explicit "Use when..." trigger clause, so the "when" is only weakly implied; per the rubric this caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords users would say ("tumor-normal", "tumor-only", "WGS", "WES", "cancer-panel", "somatic variants"), but omits a few synonyms and file extensions like FASTQ/BAM/.vcf, leaving minor coverage gaps.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (somatic tumor-normal/tumor-only calling with explicit assay subtypes) with distinct triggers and minimal conflict risk, well separated from the germline sibling skill.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.