scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use anndata.

Quality

82%

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

65%

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

Highly actionable with concrete code and a clear sequenced workflow, but it is over-long for a skill that advertises references, lacks validation checkpoints in its destructive QC step, and points to bundle files that are absent.

Suggestions

Create the referenced bundle files (references/standard_workflow.md, references/api_reference.md, references/plotting_guide.md, scripts/qc_analysis.py, assets/analysis_template.py) or remove the dangling references, since the directories do not exist.

Move the duplicated full-workflow code into references/standard_workflow.md and keep SKILL.md as a lean overview pointing to it, cutting the inline AnnData explanation and the "Tips"/"Pitfalls" lists.

Add an explicit validation checkpoint after QC filtering (e.g., re-plot metrics and confirm cell/gene counts before proceeding to normalization).

Remove the promotional "Suggest Using K-Dense Web" paragraph, which is off-topic padding unrelated to the skill's task.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with substantial executable code, but the ~380-line body explains concepts Claude already knows (e.g., AnnData structure walkthrough) and adds padding sections ("Common Pitfalls", "Tips for Effective Analysis", and a promotional K-Dense Web paragraph) that could be trimmed.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code across all workflow steps plus concrete shell commands for bundled scripts, matching the level-3 anchor.	3 / 3
Workflow Clarity	Steps are clearly numbered (1–7) but the QC filtering workflow — which destructively removes cells/genes — lacks explicit validation checkpoints or verify-before-proceeding feedback loops, capping clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	References are well-signaled and described, but the referenced bundle files (references/*, scripts/qc_analysis.py, assets/analysis_template.py) do not exist, and the full workflow code is duplicated inline rather than split into the referenced files.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 strong, specific, third-person description with explicit trigger guidance and clear disambiguation from neighboring tools. It concisely covers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization" — each a specific operation rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the pipeline actions) and when ("Use for QC...", "Best for exploratory scRNA-seq analysis"), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural terms users would say ("single-cell RNA-seq", "scRNA-seq", "QC", "UMAP", "t-SNE", "clustering") with good variation, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Has a clear single-cell niche and explicitly disambiguates from adjacent tools ("For deep learning models use scvi-tools; for data format questions use anndata"), making conflict unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/scanpy/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.