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

66%

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

57%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.

A highly actionable, well-organized body of executable cancer-genomics code with useful workflows and troubleshooting, but it inlines complete implementations that already exist as bundled scripts without ever referencing them, and multi-tool pipelines lack explicit validation checkpoints. Pointing capability sections at the existing scripts and adding verify steps would address the weakest dimensions.

Suggestions

Reference the existing bundle scripts from each capability section (e.g. 'Full CLI implementation: scripts/parse_vcf.py') and inline only the minimal pattern, cutting the duplicated ~400 lines of implementation code from SKILL.md.

Add explicit validation checkpoints to the workflows (e.g. verify PASS variant count is non-zero after filtering, confirm all four CNVkit output files exist before segmentation) with a fix-and-retry loop like the Troubleshooting section.

Fill the placeholder gaps in Workflow 4 (define PATHWAY_GENES/DRIVER_GENE sourcing, GROUP column) and add the missing antitarget-coverage step to the CNVkit pipeline so examples run as written.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-dense with little concept padding, but the Overview paragraph restates the description and roughly 400 lines of implementation (parse_vcf, NMF, DDR, TMB) duplicate code that already exists as bundle scripts, so it could be tightened substantially. Not 4 because the duplication is more than minor over-explanation.	3 / 5
Actionability	Nearly all guidance is concrete, executable Python (cyvcf2 parsing, GATK/CNVkit subprocess wrappers, NMF, Fisher's exact cohort analysis) with real parameters and outputs. Minor gaps keep it below 5: Workflow 4 uses undefined placeholders (PATHWAY_GENES, DRIVER_GENE, clin.GROUP) and the CNVkit pipeline consumes an antitarget coverage file it never creates.	4 / 5
Workflow Clarity	Multi-step workflows are clearly sequenced (call → filter → annotate → parse; coverage → reference → fix → segment), and subprocess calls fail fast via check=True, but these batch multi-tool pipelines have no explicit verify checkpoints (e.g. confirming non-empty outputs, sample counts, or PASS variant tallies before downstream analysis), matching the 'steps listed but validation implicit' anchor.	3 / 5
Progressive Disclosure	Section structure is well organized (Overview, When to Use, Quick Start, seven capabilities, workflows, troubleshooting), but the four ready-made scripts in scripts/ (parse_vcf.py, nmf_metagenes.py, ddr_network.py, calculate_tmb.py) are never referenced from the body — their full implementations are inlined instead, so content that should live one level deep is in SKILL.md. Not 2 because the section organization is solid, not 4 because bundle navigation is entirely absent.	3 / 5
	Total	13 / 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.

A specific, comprehensive capability listing in third person with explicit routing to sibling skills, but it omits any 'Use when...' trigger clause and lacks file-format and TMB trigger terms. Adding an explicit trigger sentence with natural user phrases would lift completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when processing tumor sequencing data (VCF/BAM/MAF files), calculating TMB, or analyzing copy number or expression data from cancer cohorts.'

Include natural trigger terms users actually say: '.vcf', 'MAF', 'tumor mutational burden (TMB)', 'somatic variants'.

Keep the sibling-skill routing sentences — they are effective distinctiveness signals — and place the trigger guidance alongside them.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete capability areas ('Somatic mutation detection and annotation, structural variation characterization, copy number analysis, tumor purity/ploidy estimation, NMF metagene extraction, and DNA damage response network analysis'), matching the comprehensive multi-action anchor.	5 / 5
Completeness	The 'what' is clear and comprehensive, but there is no 'Use when...' clause or equivalent trigger guidance — only deferral routing ('For cancer mutation databases use cosmic-database; for variant clinical significance use clinvar-database'), which the guidelines cap at 3. Not a 4 because the 'when' is entirely missing rather than weakly implied.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('cancer genomics', 'somatic mutation', 'copy number', 'tumor purity'), but common user variations are missing: file formats like '.vcf'/'MAF' and the phrase 'tumor mutational burden'/'TMB' are absent even though TMB is a covered capability. Not the level-5 anchor, which requires synonyms and file extensions; above level 3 because most natural domain terms are present.	4 / 5
Distinctiveness Conflict Risk	A clear cancer-genomics niche with explicit boundary routing to sibling skills (cosmic-database, clinvar-database) that actively reduces conflict risk; minimal overlap with generic bioinformatics or database skills.	5 / 5
	Total	17 / 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 (607 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: 4082a2e

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.