building-genomics-pipelines
This skill should be used when the user asks to "build a genomics pipeline", "call variants", "analyze RNA-seq", "run ChIP-seq analysis", "annotate variants", "QC sequencing data", "detect CNVs", or when writing any bioinformatics pipeline code involving NGS data. Provides expert guidance on pipeline frameworks (Nextflow, Snakemake, WDL), alignment, variant calling, and production-ready nf-core workflows.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its bioinformatics/genomics niche with explicit trigger phrases, specific capabilities, and domain-specific terminology. It effectively answers both what the skill does and when to use it, with natural user-facing language. The only minor note is that the description leads with 'when' before 'what', but both are well-covered.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technologies: pipeline frameworks (Nextflow, Snakemake, WDL), alignment, variant calling, nf-core workflows, and mentions specific analysis types like RNA-seq, ChIP-seq, CNV detection. | 3 / 3 |
Completeness | Clearly answers both 'what' (expert guidance on pipeline frameworks, alignment, variant calling, nf-core workflows) and 'when' (explicit trigger phrases listed at the beginning with 'This skill should be used when...'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'build a genomics pipeline', 'call variants', 'analyze RNA-seq', 'run ChIP-seq analysis', 'annotate variants', 'QC sequencing data', 'detect CNVs'. These are realistic user phrases in the bioinformatics domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in genomics/bioinformatics with domain-specific triggers like 'NGS data', 'variant calling', 'RNA-seq', 'ChIP-seq', and specific tools like Nextflow, Snakemake, WDL. Very unlikely to conflict with non-bioinformatics skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured overview skill that makes strong opinionated tool recommendations and is concise. However, it falls short on actionability—providing mostly tool names rather than executable commands or pipeline code snippets—and on workflow clarity, lacking explicit step-by-step sequences with validation checkpoints for the multi-step genomics workflows it describes. The referenced bundle files are missing, undermining progressive disclosure.
Suggestions
Add executable code examples for at least one complete mini-workflow (e.g., FASTQ → alignment → variant calling) with concrete commands for BWA-MEM2, samtools, and DeepVariant, including validation steps between stages.
Include an explicit numbered workflow with validation checkpoints, e.g., 'FastQC → if PASS → trim with fastp → align with BWA-MEM2 → validate with samtools flagstat → if mapping rate > 90% → call variants'.
Create the referenced bundle files (references/rnaseq.md, references/annotation.md, references/cnv.md) or remove the broken references until they exist.
Add a concrete Nextflow process definition or Snakemake rule example for custom pipeline building, since the skill description says it covers 'writing bioinformatics pipeline code'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what FASTQ, BAM, or VCF files are conceptually and instead focuses on actionable preferences (e.g., prefer CRAM over BAM, always bgzip+tabix). No unnecessary padding or explanations of concepts Claude already knows. | 3 / 3 |
Actionability | The skill provides clear opinionated tool choices and one concrete nf-core command example, but lacks executable code for custom pipeline construction (e.g., a minimal Nextflow process definition, Snakemake rule, or actual alignment/variant-calling command lines). Most guidance is at the 'use tool X' level rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | Pipeline design principles mention QC at every stage and checkpointing, but no explicit multi-step workflow with validation checkpoints is provided. There's no concrete sequence like 'run FastQC → trim → align → validate BAM → call variants → validate VCF'. The three design principles are good but abstract rather than sequenced with feedback loops. | 2 / 3 |
Progressive Disclosure | The skill references three sub-files (references/rnaseq.md, references/annotation.md, references/cnv.md) which is good structure, but no bundle files are provided, so these references are broken. Additionally, several workflow types mentioned in the description (ChIP-seq, QC) lack corresponding reference files, and the nf-core table could potentially be in a reference file to keep the overview leaner. | 2 / 3 |
Total | 9 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- provectus/awos-recruitment
- Commit
70de68f
- 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.