Name: nfcore-scrnaseq-wrapper
Rating: 58.4 (1 reviews)
Author: ClawBio

nfcore-scrnaseq-wrapper

Wrapper skill for running nf-core/scrnaseq 4.1.0 upstream single-cell RNA-seq preprocessing from FASTQ with strict preflight, reproducibility outputs, and downstream handoff to ClawBio scRNA skills.

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 ./skills/nfcore-scrnaseq-wrapper/SKILL.md

Quality

Content

70%

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

The body is highly actionable with a well-sequenced, validated workflow and concrete executable examples, but it is a monolithic document that violates progressive disclosure and is verbose enough in places to warrant tightening.

Suggestions

Split the flag reference table, the Output Structure tree, and the Gotchas into separate one-level-deep reference files (e.g. CLI_REFERENCE.md, OUTPUTS.md, GOTCHAS.md) and link to them from the overview.

Tighten the Algorithm/Methodology and Gotchas sections by removing re-derived internals (e.g. the repeated igenomes_ignore explanation and the nf-schema warning provenance) that Claude can infer from the pinned pipeline version.

Actually bundle the referenced modules (samplesheet_builder.py, preflight.py, demo/README.md) so the named references resolve to real navigable files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and high-signal, but several Gotchas and the Algorithm/Methodology section restate implementation internals at length (nf-schema warning provenance, macOS VirtioFS details, repeated igenomes_ignore logic) that goes beyond what is needed to act, so it could be tightened.	2 / 3
Actionability	It provides fully executable copy-paste bash commands, a complete flag reference table with types and defaults, a concrete output tree, and an example result.json, matching the anchor for copy-paste-ready concrete guidance.	3 / 3
Workflow Clarity	The 7-step pipeline is clearly sequenced with explicit validation checkpoints (preflight gates, 'no subsequent step runs', required-output checks after Nextflow exits) and feedback loops (structured SkillError with error_code and fix hint, strict resume-compatibility checks).	3 / 3
Progressive Disclosure	It is a ~54KB monolithic SKILL.md with no bundled reference, scripts, or assets directories, and content that should be split (the long flag table, the Gotchas, the output tree) is inline; named module references are not organized as navigable one-level-deep files.	1 / 3
	Total	9 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and clearly delineated within a narrow niche, but it omits an explicit 'Use when...' trigger clause and relies on technical phrasing rather than natural user keywords, leaving completeness and trigger-term quality mid-range.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g. 'Use when running 10x scRNA preprocessing from FASTQ, or when the user mentions STARsolo/alevin-fry/kb-python upstream processing').

Soften technical jargon like 'upstream single-cell RNA-seq preprocessing' with user-facing phrasings such as 'FASTQ to h5ad for single-cell RNA-seq'.

Surface one or two of the frontmatter trigger_keywords directly in the description so 'when to use it' is answered in-band.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'running nf-core/scrnaseq 4.1.0 upstream single-cell RNA-seq preprocessing from FASTQ', 'strict preflight', 'reproducibility outputs', and 'downstream handoff' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' the skill does but lacks any explicit 'when/Use when' trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	It contains some relevant keywords (FASTQ, single-cell RNA-seq, scRNA) but uses technical phrasing like 'upstream preprocessing' rather than the natural variations a user would actually say; the explicit trigger keywords live in frontmatter metadata, not the description.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — nf-core/scrnaseq 4.1.0, upstream FASTQ preprocessing, and ClawBio scRNA handoff — making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: ClawBio/ClawBio
Path: skills/nfcore-scrnaseq-wrapper/SKILL.md
Commit: f6c7851

Reviewed: 2 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.