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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill scanpyOverall
score
86%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 a specific bioinformatics domain (single-cell RNA-seq analysis), lists concrete analytical capabilities, and explicitly distinguishes itself from related skills. The description uses appropriate third-person voice and includes both positive triggers ('Use for...') and negative boundaries (when to use other skills instead).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: QC, normalization, dimensionality reduction (with specific methods PCA/UMAP/t-SNE), clustering, differential expression, and visualization. | 3 / 3 |
Completeness | Clearly answers both what (QC, normalization, dimensionality reduction, clustering, differential expression, visualization) and when ('Use for...', 'Best for exploratory scRNA-seq analysis'). Also provides explicit guidance on when NOT to use it (deep learning → scvi-tools, data format → anndata). | 3 / 3 |
Trigger Term Quality | Includes natural technical terms users would say: 'single-cell RNA-seq', 'scRNA-seq', 'QC', 'normalization', 'PCA', 'UMAP', 't-SNE', 'clustering', 'differential expression'. These are standard vocabulary in the bioinformatics domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (single-cell RNA-seq analysis) and explicit differentiation from related skills (scvi-tools for deep learning, anndata for data formats). Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill with excellent code examples and good progressive disclosure structure. The main weaknesses are moderate verbosity (including unnecessary promotional content and explanatory text Claude doesn't need) and missing explicit validation checkpoints in the workflow, particularly for quality control decisions and intermediate analysis steps.
Suggestions
Remove the 'When to Use This Skill' section and the K-Dense promotional paragraph - these add tokens without actionable value
Add explicit validation checkpoints after QC filtering (e.g., 'Verify cell count is reasonable: print(adata.shape)') and after clustering (e.g., 'Check cluster sizes are balanced')
Trim explanatory phrases like 'The AnnData object is the core data structure' - Claude knows this; just show the structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'The AnnData object is the core data structure in scanpy') and could be tightened. The 'When to Use This Skill' section largely duplicates information Claude can infer. The promotional K-Dense section at the end is unnecessary padding. | 2 / 3 |
Actionability | Excellent executable code throughout with copy-paste ready examples for every major operation. Includes specific commands, complete function calls with parameters, and concrete workflows from data loading through saving results. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but validation checkpoints are largely missing. For operations like batch correction or trajectory inference, there's no explicit validation step. The QC section mentions visualization but doesn't establish a clear validate-fix-retry loop for filtering decisions. | 2 / 3 |
Progressive Disclosure | Well-structured with clear overview, quick start, and detailed sections. References to external files (scripts/qc_analysis.py, references/plotting_guide.md, etc.) are clearly signaled and one level deep. Content is appropriately split between inline examples and referenced materials. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
88%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 |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
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.