cnv-caller-plotter

Detect copy number variations from whole genome sequencing data and generate publication-quality genome-wide CNV plots. Supports CNV calling, segmentation, and visualization for cancer genomics and rare disease analysis.

Quality

60%

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 ./scientific-skills/Data Analysis/cnv-caller-plotter/SKILL.md

Quality

Content

45%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 comprehensive and well-structured into sections, but it is heavily padded with template boilerplate and monolithic inlining that should live in separate reference files, and its executable examples overstate a stub backend. Tightening and splitting would materially improve token efficiency and navigation.

Suggestions

Move the Core Capabilities detail, Common Patterns, Troubleshooting, and Common Pitfalls into dedicated files under references/ and link to them from SKILL.md to fix progressive disclosure.

Delete the verbatim description repeats in 'When to Use'/'Key Features' and the generic template sections (Output Requirements, Response Template, Input Validation, Output Contract) that restate obvious guidance.

Reconcile the 'References' section with the actual references/runtime_checklist.md file, and either implement or clearly mark as illustrative the undefined identify_somatic() and stub call_cnvs() logic.

Dimension	Reasoning	Score
Conciseness	The ~1180-line body is noticeably verbose: the 'When to Use' and 'Key Features' sections restate the description verbatim, and large generic template blocks ('Output Requirements', 'Response Template', 'Input Validation') add padding that does not earn its tokens.	2 / 5
Actionability	Concrete code and CLI commands are provided, but the packaged scripts/main.py is a stub returning hardcoded data and the 'Complete Workflow' references an undefined identify_somatic() helper, leaving a gap between the guidance and what actually executes.	3 / 5
Workflow Clarity	A clear sequenced 'Workflow' plus pre/during/post 'Quality Checklist' and an explicit fallback path ('If execution fails... switch to the fallback path') provide most checkpoints, with only minor validation gaps in the script itself.	4 / 5
Progressive Disclosure	Nearly all material (six core capabilities, four usage patterns, pitfalls, troubleshooting) is inlined into SKILL.md rather than split into reference files, and the 'References' section incorrectly states '(No reference files currently available)' despite references/runtime_checklist.md existing.	2 / 5
	Total	11 / 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 good natural trigger terms, but it lacks an explicit 'Use when...' clause, capping completeness at 3. Adding concrete usage-trigger guidance and file-extension keywords would raise the remaining dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to call CNVs from BAM/VCF files, generate genome-wide CNV plots, or analyze cancer/rare-disease copy number data.'

Include natural file extensions users mention (.bam, .vcf, .bed) to push trigger term coverage to comprehensive.

Keep the third-person voice but tighten 'Supports CNV calling, segmentation, and visualization' since it partially restates the opening sentence.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Detect copy number variations', 'generate publication-quality genome-wide CNV plots', 'CNV calling, segmentation, and visualization' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Has a clear 'what' but no explicit 'Use when...' trigger clause in the description itself, which per the judging guidelines caps completeness at 3; the 'when' guidance lives only in the body, not the description.	3 / 5
Trigger Term Quality	Strong natural term coverage including synonyms ('copy number variations' / 'CNVs', 'whole genome sequencing' / implied WGS, 'cancer genomics', 'rare disease'), but omits file extensions users would mention (.bam, .vcf) so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CNV calling and genome-wide plotting from WGS data) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1180 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/cnv-caller-plotter/SKILL.md
Commit: f5ef65b

Reviewed: 25 minutes 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.