Tessl • The package manager for agent skills

SkillPublic

ngs-scrna-seq

Route single-cell or single-nucleus RNA-seq FASTQs to public count-generation workflows and defer post-count matrix QC, annotation, clustering, and UMAP analysis to the embedded scrna-seq-qc skill.

Quality

78%

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 ./plugins/ngs-analysis/skills/ngs-scrna-seq/SKILL.md

Quality

Content

75%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 well-structured, executable body: concrete commands with explained flags, an ordered workflow with preflight and readiness gating, and clean deferral of post-count work to the embedded skill. Remaining gaps are a missing samplesheet example, no explicit error-recovery loop, and some plugin-internal jargon.

Suggestions

Add a minimal samplesheet.csv example so the kickoff commands are runnable as-is.

Include a brief validate-and-retry loop (e.g. what to do when preflight or resource readiness fails) before --execute.

Dimension	Reasoning	Score
Conciseness	The body is efficient with command-driven sections, a checklist of inputs, and guardrails, without explaining concepts Claude already knows. Minor tightening is possible, e.g. the plugin-internal phrase 'Treat scRNA as three ordered rows in the plugin state'.	4 / 5
Actionability	Fully formed, copy-paste ready commands are given for preflight and both execution paths, with flag meanings explained ('--revision <tag>', '--bundle-root <bundle>=<path>', '--require-resource-plan'). The main gap is the absence of a concrete samplesheet example or expected output fields.	4 / 5
Workflow Clarity	The three-row ordered sequence (FASTQ-to-count, post-count QC/annotation, downstream stats) plus a preflight step and readiness gating ('--execute only when Nextflow plus a container/HPC profile are ready') provide clear checkpoints. It falls short of a 5 because there is no explicit validate-fail-fix-retry feedback loop for these batch pipeline runs.	4 / 5
Progressive Disclosure	No bundle files exist; the body is well-sectioned and appropriately defers all post-count QC detail to the embedded scrna-seq-qc skill rather than inlining it. It does not reach 5 because the skill exceeds 50 lines and the embedded-skill and plugin-script references are path mentions without navigation detail in this bundle.	4 / 5
	Total	16 / 20 Passed

Description

70%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 distinct, concrete description with good natural trigger terms and an explicit boundary against the embedded QC skill. Its main weakness is the absence of any explicit 'when to use' trigger clause and missing common synonyms/file extensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user provides scRNA-seq/snRNA-seq FASTQs or asks for count matrices from single-cell data.'

Include common synonyms and file extensions users would naturally say, such as 'scRNA-seq', '.h5', '.h5ad', and '.rds'.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ('Route single-cell or single-nucleus RNA-seq FASTQs to public count-generation workflows', 'defer post-count matrix QC, annotation, clustering, and UMAP analysis to the embedded scrna-seq-qc skill'), but omits supported input formats (.h5, .h5ad, .rds) and the specific public backends named in the body, leaving minor coverage gaps.	4 / 5
Completeness	The 'what' is clear and concrete (route FASTQs to count workflows; defer post-count analysis to the embedded skill), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. It is not a 2 because the 'what' is specific rather than vague.	3 / 5
Trigger Term Quality	Natural user terms like 'single-cell', 'single-nucleus', 'RNA-seq', 'FASTQs', 'QC', 'clustering', and 'UMAP' are present, but common synonyms and extensions users would say ('scRNA-seq', '.h5', '.h5ad', '.rds') are missing.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (upstream FASTQ-to-count routing) and explicitly disambiguates from the closely related embedded scrna-seq-qc skill by stating post-count work is deferred there, minimizing wrong-skill triggering.	5 / 5
	Total	16 / 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-scrna-seq/SKILL.md
Revision: 0722921

Reviewed: 23 days ago

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.

ngs-scrna-seq

Table of Contents

Is this your skill?