single-cell-rnaseq-pipeline
Generate single-cell RNA-seq analysis code templates for Seurat and Scanpy, supporting QC, clustering, visualization, and downstream analysis. Trigger when users need scRNA-seq analysis pipelines, preprocessing workflows, or batch correction code.
88
86%
Does it follow best practices?
Impact
90%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
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 a strong skill description that clearly defines a specialized bioinformatics niche. It lists concrete capabilities, includes domain-specific trigger terms that users would naturally use, and explicitly states both what the skill does and when to use it. The technical specificity (Seurat, Scanpy, scRNA-seq) ensures minimal conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'QC, clustering, visualization, and downstream analysis' along with 'preprocessing workflows' and 'batch correction code'. Names specific tools (Seurat, Scanpy) and domain (single-cell RNA-seq). | 3 / 3 |
Completeness | Clearly answers both what ('Generate single-cell RNA-seq analysis code templates...supporting QC, clustering, visualization, and downstream analysis') and when ('Trigger when users need scRNA-seq analysis pipelines, preprocessing workflows, or batch correction code'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'scRNA-seq', 'single-cell RNA-seq', 'Seurat', 'Scanpy', 'QC', 'clustering', 'batch correction', 'preprocessing workflows', 'analysis pipelines'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche with distinct triggers - single-cell RNA-seq is a specialized bioinformatics domain, and naming specific tools (Seurat, Scanpy) makes it very unlikely to conflict with general coding or data analysis skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable scRNA-seq analysis templates with excellent code examples and clear organization. However, it suffers from unnecessary boilerplate sections (security checklists, lifecycle status, evaluation criteria) that consume tokens without adding value for Claude. The workflow could benefit from explicit validation checkpoints between major analysis steps.
Suggestions
Remove or significantly condense the Risk Assessment, Security Checklist, Evaluation Criteria, and Lifecycle Status sections - these are boilerplate that don't help Claude generate better code
Add explicit validation checkpoints in workflows, e.g., 'After QC filtering, verify cell count with print(adata.shape) before proceeding' or 'Check PCA variance explained before selecting n_pcs'
Consolidate the parameter tables and recommendations into more compact formats to reduce token usage while preserving information
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose with redundant sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that add little value. The core technical content is reasonably efficient, but boilerplate sections inflate token count unnecessarily. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for both Seurat and Scanpy workflows. Command-line parameters are clearly documented with a table, and code snippets are complete with imports and realistic function calls. | 3 / 3 |
Workflow Clarity | The code examples show clear sequential steps (load → QC → normalize → cluster → visualize), but lacks explicit validation checkpoints. For a complex bioinformatics pipeline, there should be verification steps after QC filtering and before proceeding to downstream analysis. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to quick start to detailed examples. References to external files (references/seurat_template.R, etc.) are clearly signaled and one level deep. Content is appropriately split between inline examples and referenced detailed templates. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- 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.