Name: nfcore-scrnaseq-wrapper
Rating: 60 (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

71%

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

77%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.

The content is highly actionable with executable commands, exhaustive flag documentation, and a rigorously validated 7-step workflow — a strong reference for a complex pipeline wrapper. Its main weaknesses are verbosity in the Gotchas section and a monolithic structure that inlines content which could live in separate reference files for easier navigation.

Suggestions

Trim the longest Gotchas paragraphs (validation.* warning, macOS Docker workaround) to the actionable rule plus a one-line rationale; move deep context into a separate REFERENCE.md.

Split the large CLI flag table and/or detailed preset/compatibility policy into one-level-deep reference files (e.g. CLI.md, PRESETS.md) with clear 'See X.md' links from the overview.

Verify the prose-referenced scripts (preflight.py, params_builder.py, assets/schema_input.json) actually exist as bundle files, or remove the file-name references so readers are not pointed at missing material.

Dimension	Reasoning	Score
Conciseness	The body is packed with genuinely niche, non-obvious knowledge (4.1.0 quirks, CellBender stochasticity, macOS Docker workarounds), but the Gotchas section contains several very long explanatory paragraphs (e.g. the validation.* warning, the macOS Docker block) that could be tightened without losing the actionable point.	3 / 5
Actionability	The CLI Reference provides many complete, copy-paste-ready bash commands covering standard, demo, STARsolo, kallisto, CellRanger Multi, and air-gapped cases, plus an exhaustive flag table and concrete result.json/report.md examples.	5 / 5
Workflow Clarity	The strictly ordered 7-step algorithm is clearly sequenced with explicit validation checkpoints (preflight before execution, structured SkillError with error_code/fix, required-output checks after Nextflow exits, --resume checksum verification), giving strong feedback loops for a destructive/batch operation.	5 / 5
Progressive Disclosure	The file is well-sectioned with clear headers, but at ~430 lines it is monolithic: the large CLI flag table and the very long Gotchas section are inlined rather than split into one-level-deep reference files, and the prose-named scripts (preflight.py, params_builder.py, assets/schema_input.json) have no bundled references to navigate to.	3 / 5
	Total	16 / 20 Passed

Description

66%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.

The description is specific and distinct, clearly stating the pipeline, version, and core capabilities, but it omits any explicit 'Use when...' trigger guidance, which caps completeness. Adding a trigger clause with a few more natural synonyms (10x, h5ad, STARsolo) would raise both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming the situations that should fire this skill (e.g. running scrnaseq from raw FASTQ, preprocessing 10x Chromium data, generating .h5ad from single-cell FASTQs).

Include a few more natural trigger terms/synonyms users say (10x, h5ad, STARsolo, alevin-fry) so the description itself — not just metadata.trigger_keywords — carries them.

Keep the third-person voice but consider naming the canonical output (preferred_h5ad) to sharpen the 'what' for downstream chaining.

Dimension	Reasoning	Score
Specificity	Names the domain ('nf-core/scrnaseq 4.1.0 upstream single-cell RNA-seq preprocessing from FASTQ') and several concrete actions ('strict preflight', 'reproducibility outputs', 'downstream handoff'), but a couple of pipeline-specific capabilities (preset selection, output resolution) are only implied.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural keyword coverage (single-cell RNA-seq, scRNA, FASTQ, scrnaseq, preprocessing), but common synonyms and extensions a user might say (10x, h5ad, STARsolo, alevin-fry, .fastq) are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	The FASTQ-to-preprocessing niche is clearly distinguished from downstream scRNA analysis, with minor overlap risk against related ClawBio scRNA skills that the body explicitly routes around.	4 / 5
	Total	15 / 20 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: 00f070d

Reviewed: 4 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.