cancer-genomics-analysis

Computational cancer genomics workflows. Somatic mutation detection and annotation, structural variation characterization, copy number analysis, tumor purity/ploidy estimation, NMF metagene extraction, and DNA damage response network analysis. For cancer mutation databases use cosmic-database; for variant clinical significance use clinvar-database.

Quality

71%

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 ./backend/cli/skills/biology/cancer-genomics-analysis/SKILL.md

Quality

Content

61%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 highly actionable with executable code throughout, but it is over-inlined — duplicating bundle scripts and omitting validation checkpoints in pipeline workflows — which hurts conciseness, workflow clarity, and progressive disclosure.

Suggestions

Replace the full inline implementations of capabilities that already exist in scripts/ (e.g. parse_vcf.py, calculate_tmb.py, nmf_metagenes.py, ddr_network.py) with brief summaries plus links to those files, keeping only a short Quick Start inline.

Add explicit validation checkpoints to the Typical Workflows — e.g. after Mutect2 filtering and SnpEff annotation, verify the output VCF is non-empty and tabix-indexed before parsing, with a fix-and-retry loop on failure.

Add a "Bundle scripts" or "References" section that lists and links each script in scripts/ so the file structure is discoverable from SKILL.md.

Dimension	Reasoning	Score
Conciseness	Prose is tight and avoids explaining basics Claude already knows, but ~530 lines fully inline seven capabilities plus three end-to-end workflows — content that exists as parallel bundle scripts is duplicated inline rather than referenced, which could be tightened.	3 / 5
Actionability	Every capability is backed by concrete, copy-paste-ready Python with real function signatures, library calls, and output examples covering the common cases across VCF parsing, Mutect2, SVs, CNVkit, NMF, DDR networks, and TMB.	5 / 5
Workflow Clarity	The three "Typical Workflows" give clear numbered sequences, but they drive subprocess-based pipeline/batch operations with no validation or verification checkpoints and no error-feedback loop, so per the rubric workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	The body is monolithic: bundle scripts exist in scripts/ (calculate_tmb.py, ddr_network.py, nmf_metagenes.py, parse_vcf.py) that parallel the inline implementations, but the body never references or links to them, so content that belongs in separate files is inlined with no navigation.	2 / 5
	Total	13 / 20 Passed

Description

82%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, distinctive, and rich in natural trigger terms, but lacks an explicit "Use when..." trigger clause, which caps completeness. Adding a concrete when-to-use sentence would lift it to the top band.

Suggestions

Add an explicit trigger clause such as "Use when processing somatic variant calls, copy-number profiles, or expression signatures from tumor sequencing data."

Keep the existing deferral routing to cosmic-database and clinvar-database — it strengthens distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "Somatic mutation detection and annotation", "structural variation characterization", "copy number analysis", "tumor purity/ploidy estimation", "NMF metagene extraction", and "DNA damage response network analysis" — giving comprehensive coverage of the domain.	5 / 5
Completeness	Has a clear "what" (the full capability list) but no explicit "Use when..." trigger clause; the trailing "For cancer mutation databases use cosmic-database" sentences are routing/deferral guidance rather than when-to-use guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes the natural vocabulary a cancer genomics user would actually say — somatic mutation, structural variation, copy number, tumor purity/ploidy, NMF metagene, DNA damage response — with comprehensive coverage of the domain's terms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (computational cancer genomics pipelines) and explicitly defers adjacent tasks to other skills ("use cosmic-database", "use clinvar-database"), minimizing overlap and conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (543 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/cancer-genomics-analysis/SKILL.md
Commit: 3a6c3a9

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.