ngs-bulk-rnaseq

Dispatch bulk RNA-seq requests to FASTQ-to-count QC or count-matrix differential-expression skills using nf-core/rnaseq, STAR, Salmon, featureCounts, MultiQC, and R/Bioconductor workflows.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/ngs-analysis/skills/ngs-bulk-rnaseq/SKILL.md

Quality

Content

73%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.

Highly actionable with executable commands and a sensible dispatch order, but workflow clarity is capped by missing explicit validation checkpoints for batch/destructive runs, and progressive disclosure is hampered by heavy inlining of repeated command blocks with no bundle files to offload detail.

Suggestions

Add explicit validation checkpoints (e.g. verify preflight install plan, check run_manifest.json/validation/ before proceeding) to lift workflow clarity past the batch cap.

Move the duplicated runner command block and preflight variants into scripts/ or a references/ file and link once, rather than repeating inline.

De-duplicate the run_bulk_rnaseq_counts_qc.py invocation, which appears nearly verbatim in both Plugin-Owned Local Paths and Kickoff Pattern.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — short section headers, confirm-list, and copy-paste commands with minimal preamble — but a few explanatory sentences ('The local runners create a standard run envelope...', 'Do not depend on development-only eval harness paths') edge slightly past essential, keeping it just below 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready command blocks for both runners, preflight, and the nextflow kickoff skeleton with concrete flags (--genome GRCh38, --aligner star_salmon), covering the common cases end to end.	5 / 5
Workflow Clarity	Sequencing is present (preflight, dispatch order, kickoff, downstream gating) with an explicit batch gate ('start differential expression only after the raw count matrix... are confirmed'), but preflight/run commands lack explicit validation checkpoints and the destructive/batch cap holds it at 3.	3 / 5
Progressive Disclosure	Good sectioning, but several full command blocks (preflight variants, kickoff skeleton, local runner repeated twice) are inlined rather than referenced out to bundle files, and no references/ scripts/ assets/ bundle exists to offload detail, so structure could be better split.	3 / 5
	Total	15 / 20 Passed

Description

62%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, tool-rich description that clearly conveys its dispatcher role and routes to two named sub-skills. Its main gap is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a user requests bulk RNA-seq analysis from FASTQs or a count matrix.'

Include a few synonyms/extensions (transcriptomics, .fastq, .bam) to broaden natural trigger term coverage.

Frame the tool list as discrete capability actions rather than a passive workflow stack.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions — 'Dispatch bulk RNA-seq requests', 'Route FASTQ/BAM processing to count-generation QC' — naming specific tools (nf-core/rnaseq, STAR, Salmon, featureCounts); not quite 5 since it lists tools more as a stack than enumerated discrete actions.	4 / 5
Completeness	It clearly states what the skill does (dispatches bulk RNA-seq requests to two sub-skills) but has no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by 'Dispatch... to', so per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes strong natural terms ('bulk RNA-seq', 'FASTQ', 'count matrix', 'differential expression', 'QC') that users would say, but omits common synonyms like 'transcriptomics' or file extensions like '.fastq' that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	The dispatcher niche is fairly distinct and routes to two specifically-named sub-skills, with minimal overlap risk against generic ngs skills; slight residual overlap with sibling ngs dispatchers keeps it just below 5.	4 / 5
	Total	15 / 20 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/SKILL.md
Commit: d416fd5

Reviewed: 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.