bulk-rnaseq

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.

Quality

92%

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

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured orchestration skill with executable commands, real referenced bundle files, clear sequencing, and a validation gate. The main weakness is verbosity — content overlaps across the Overview, Pipeline-at-a-glance, and Stage-by-Stage sections and the pitfall list is exhaustive.

Suggestions

Collapse the overlapping stage descriptions between 'The Pipeline at a Glance', 'Stage-by-Stage Workflow', and the bridge section into a single canonical sequence to cut repeated tokens.

Trim the nine-item Common Pitfalls list to the highest-impact items (replicates, confounded batch, strandedness, non-integer/TPM counts) and move the rest into references/design-and-qc.md.

Tighten the 'Defensible' framing in the Overview — the three-bullet definition largely restates practices already enforced later in the workflow stages.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes domain competence (no beginner explanations of RNA-seq concepts), but the body runs long — the full nine-item pitfall list, repeated stage descriptions across Overview/Pipeline/Stage-by-Stage, and the 'defensible' framing add tokens that a competent model largely already knows.	2 / 3
Actionability	Provides copy-paste-ready commands for both paths (nf-core run invocations, fastp/salmon one-liners, conda env, bridge script invocations) plus exact output file paths and column selections; scripts referenced are real and runnable.	3 / 3
Workflow Clarity	The stage-by-stage workflow is a clear numbered sequence with an explicit validation checkpoint (validate_samplesheet.py before compute) and QC gates invoked before, during, and after quantification, matching the feedback-loop pattern for batch operations.	3 / 3
Progressive Disclosure	SKILL.md is an overview that one-level-deep references four self-contained reference files and two scripts, all of which exist on disk; each reference is clearly signaled with its scope and there is no nested/deep chaining.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, specific description with concrete per-stage tooling, natural trigger phrases, and explicit when-to-use guidance plus single-cell disambiguation. It is on the longer side but every clause is load-bearing rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — QC/trimming (FastQC, fastp/Trim Galore), alignment/quantification (STAR, Salmon, featureCounts), counts-matrix assembly, DE (pydeseq2), enrichment, and figures — naming the actual tools per stage.	3 / 3
Completeness	Explicitly answers both what (full read-to-pathway orchestration) and when ('Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow') with multiple explicit trigger clauses.	3 / 3
Trigger Term Quality	Includes natural phrasings a user would say ('analyze my RNA-seq', 'FASTQ to DESeq2', 'run nf-core/rnaseq', 'STAR/Salmon quantification', 'go from reads to differentially expressed genes and enriched pathways') alongside tool keywords.	3 / 3
Distinctiveness Conflict Risk	Carves a clear bulk-RNA-seq niche and explicitly disambiguates the nearest neighbor ('For single-cell RNA-seq use the scanpy skill instead'), reducing wrong-skill triggers.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/bulk-rnaseq/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours 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.