ngs-bulk-rnaseq-counts-qc

Run or plan bulk RNA-seq FASTQ-to-count processing with sample-sheet, strandedness, genome annotation, alignment or pseudoalignment, MultiQC, and count-matrix QC checks.

Quality

85%

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

87%Weight 40%Scale 1-3

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

A tight, executable skill body with concrete runner and preflight commands and clean sectioning, assuming Claude's domain competence throughout. Its main gap is that validation/checkpoint guidance for this batch operation is implicit in prose rather than an explicit numbered validate-and-retry loop.

Suggestions

Consolidate the validation path into one explicit sequenced checklist (e.g., 1. preflight --emit-install-plan, 2. validate without --execute, 3. only when valid add --execute) so the validate -> fix -> re-run loop is unambiguous.

State the failure-recovery action when QC metrics (mapping rate, library-type agreement, outliers) are out of bounds, so the workflow_clarity checkpoint closes the loop.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no preamble explaining what RNA-seq, Salmon, or MultiQC are; every section (inputs, route, decision points, outputs) earns its place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands: the run_bulk_rnaseq_counts_qc.py runner with concrete flags (--sample-sheet, --execute, --no-dry-run) and the ngs_preflight.py preflight invocations.	3 / 3
Workflow Clarity	Steps are sequenced and validation hooks exist (preflight, dry-run/--execute distinction) but they are spread across prose rather than a single explicit validate -> fix -> re-run feedback loop, which caps a batch operation at 2.	2 / 3
Progressive Disclosure	Single well-sectioned overview file (Essential Inputs, Route, Decision Points, Outputs) with no nested document references; the only referenced paths are executable scripts, and no bundle files exist to require further splitting.	3 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

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, domain-rich description that names concrete actions and natural trigger terms, but it omits an explicit 'Use when...' clause, leaving the invocation trigger implied rather than stated. Adding a 'Use when...' sentence would raise completeness and reinforce distinctiveness against sibling RNA-seq skills.

Suggestions

Add an explicit 'Use when...' clause naming when to invoke this skill (e.g., 'Use when starting from FASTQ or aligned reads to produce gene/transcript count matrices and per-sample QC').

Briefly distinguish the trigger from the sibling differential-expression skill in the description itself, not only the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and pipeline components — 'FASTQ-to-count processing', 'sample-sheet, strandedness, genome annotation, alignment or pseudoalignment, MultiQC, and count-matrix QC checks' — rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (FASTQ-to-count processing and QC checks) but lacks an explicit 'Use when...' trigger clause, so 'when' is only implied — which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Uses natural domain terms a bioinformatician would actually say: 'bulk RNA-seq', 'FASTQ-to-count', 'sample-sheet', 'strandedness', 'MultiQC', 'count-matrix QC'.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (bulk RNA-seq read processing to counts) with specific FASTQ-to-count framing unlikely to conflict with unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/ngs-analysis/skills/ngs-bulk-rnaseq-counts-qc/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.