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.

1.51x

Quality

75%

Does it follow best practices?

Impact

82%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/scanpy/SKILL.md

Quality

Discovery

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.

This is an excellent skill description that clearly defines its scope within the bioinformatics domain. It lists specific concrete actions, uses natural domain-specific trigger terms, explicitly states when to use it, and proactively distinguishes itself from related skills (scvi-tools, anndata). The description is concise yet comprehensive, and uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. These are well-defined bioinformatics operations.	3 / 3
Completeness	Clearly answers both 'what' (QC, normalization, dimensionality reduction, clustering, DE, visualization) and 'when' ('Use for... exploratory scRNA-seq analysis with established workflows'). Also includes explicit negative triggers directing users to other skills (scvi-tools for deep learning, anndata for data format questions).	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'scRNA-seq', 'QC', 'normalization', 'PCA', 'UMAP', 't-SNE', 'clustering', 'differential expression', 'single-cell RNA-seq'. These are the exact terms bioinformaticians use when requesting these analyses.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche in single-cell RNA-seq analysis. Explicitly differentiates itself from related skills (scvi-tools and anndata) by specifying boundary conditions, making conflict very unlikely.	3 / 3
	Total	12 / 12 Passed

Implementation

50%

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

The skill provides a comprehensive and highly actionable scanpy workflow with excellent executable code examples covering the full single-cell analysis pipeline. However, it is significantly over-verbose — much of the content (AnnData structure explanation, parameter tables, best practices lists, external resource links) is either already known to Claude or duplicates what the referenced bundle files should contain. The workflow lacks explicit validation checkpoints between steps, which is important for a multi-step analytical pipeline where early errors compound.

Suggestions

Cut the 'When to Use This Skill' section, 'Understanding AnnData Structure' section, 'Additional Resources' section, and 'Tips for Effective Analysis' section — these explain things Claude already knows or duplicate the description/bundle content.

Move the 'Key Parameters to Adjust' table and 'Common Pitfalls' list into the references/standard_workflow.md bundle file to reduce the main skill's token footprint.

Add explicit validation checkpoints in the workflow, e.g., 'Verify cell count after filtering: print(adata.shape)', 'Check UMAP for batch effects before clustering', 'Confirm marker genes are biologically meaningful before annotation'.

Reduce overlap between inline content and referenced bundle files — the main SKILL.md should be a concise overview pointing to the detailed references rather than containing the full workflow inline.

Dimension	Reasoning	Score
Conciseness	The skill is highly verbose, explaining concepts Claude already knows (AnnData structure, what QC is, what UMAP/PCA are). The 'When to Use This Skill' section restates the description. The 'Understanding AnnData Structure' section, 'Key Parameters to Adjust' tables, and extensive 'Common Pitfalls' list add significant token overhead. The 'Additional Resources' section with external URLs and paper citations is unnecessary padding.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready Python code throughout. Every step of the workflow includes concrete code examples with specific function calls, parameters, and realistic usage patterns. The QC script invocation and template usage are also concrete.	3 / 3
Workflow Clarity	The workflow is clearly sequenced with numbered steps (1-7) covering the full pipeline. However, there are no explicit validation checkpoints or feedback loops — no 'verify your filtering didn't remove too many cells' or 'check clustering quality before proceeding' gates. For a multi-step pipeline where early mistakes propagate, this is a notable gap.	2 / 3
Progressive Disclosure	The skill references bundled resources (scripts/qc_analysis.py, references/standard_workflow.md, references/api_reference.md, references/plotting_guide.md, assets/analysis_template.py) with clear descriptions, but no bundle files were actually provided. The main SKILL.md also contains extensive inline content (full workflow, common tasks, parameter tables) that significantly overlaps with what the referenced standard_workflow.md and api_reference.md would contain, suggesting poor content splitting.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: K-Dense-AI/claude-scientific-skills
Commit: cbcae7b

Reviewed: 1 day 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.