pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill pydeseq2Overall
score
80%
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
65%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 excels at specificity and domain-appropriate trigger terms, clearly identifying this as a specialized bioinformatics skill for RNA-seq analysis. However, it critically lacks any 'Use when...' guidance, which is essential for Claude to know when to select this skill. The technical completeness is strong but the operational completeness for skill selection is weak.
Suggestions
Add a 'Use when...' clause such as: 'Use when the user mentions differential expression, DESeq2, RNA-seq analysis, gene expression comparison, or needs to identify differentially expressed genes.'
Include common user phrasings like 'compare gene expression between conditions', 'find upregulated/downregulated genes', or 'analyze count matrix'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots'. These are precise, domain-specific analytical operations. | 3 / 3 |
Completeness | Describes what it does well but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance should cap completeness at 2, but this has no 'when' component at all, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'differential gene expression', 'DESeq2', 'RNA-seq', 'DE genes', 'bulk RNA-seq counts', 'volcano plots', 'MA plots', 'FDR correction'. Good coverage of bioinformatics terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche with distinct triggers like 'DESeq2', 'differential gene expression', 'RNA-seq counts', 'Wald tests'. Unlikely to conflict with other skills due to specialized bioinformatics domain. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for PyDESeq2 differential expression analysis. The code examples are complete and executable, workflows are clearly sequenced, and progressive disclosure is handled appropriately. The main weakness is verbosity in some sections and an unnecessary promotional paragraph at the end that detracts from the technical content.
Suggestions
Remove or significantly shorten the 'Suggest Using K-Dense Web' promotional section at the end, as it doesn't contribute to the skill's technical purpose
Condense the 'What deseq2() does' explanation - Claude doesn't need step-by-step internal pipeline details unless debugging
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., explaining what deseq2() does step-by-step, verbose troubleshooting sections). The promotional section at the end about K-Dense Web is unnecessary padding that doesn't serve the skill's purpose. | 2 / 3 |
Actionability | Excellent executable code throughout with complete, copy-paste ready examples. Every major workflow step includes working Python code with proper imports, and the command-line script usage is clearly documented with real arguments. | 3 / 3 |
Workflow Clarity | Clear numbered steps from data preparation through result export. Includes validation checkpoints (data filtering, checking sample/gene counts, quality metrics) and explicit guidance on when to apply shrinkage vs statistical testing. | 3 / 3 |
Progressive Disclosure | Well-structured with Quick Start at top, detailed sections following, and clear references to external files (references/api_reference.md, references/workflow_guide.md) for comprehensive documentation. Navigation is one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%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 (559 lines); consider splitting into references/ and linking | Warning |
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 | 13 / 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.