pydeseq

Differential gene expression analysis for bulk RNA-seq count matrices using a DESeq2-like workflow in Python; use when you need Wald tests, FDR correction, and optional LFC shrinkage for condition/batch/covariate designs.

Quality

83%

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

75%Weight 40%Scale 1-5

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

The body is highly actionable with a complete executable pipeline and well-organized one-level-deep references that are real files, but it leans verbose by re-explaining familiar DESeq2 concepts and inlining plotting code that would fit better in a reference.

Suggestions

Trim or move familiar exposition: the 'What dds.deseq2() does' dispersion-trend enumeration and the dependency rationale restate DESeq2 knowledge Claude already has — shorten these or push them to references/workflow_guide.md.

Move the full minimal-volcano-plot code block into references/workflow_guide.md or scripts/run_deseq2_analysis.py, keeping only a one-line pointer in the main example.

Add an explicit validation checkpoint after fitting/testing (e.g., assert dds.varm is populated, confirm res has expected columns and padj distribution) before the export step to strengthen the feedback loop for this batch analysis.

Dimension	Reasoning	Score
Conciseness	The 'What dds.deseq2() does' enumeration and dependency list re-explain DESeq2 concepts Claude already knows, and the full inline volcano-plot block is padding that belongs in a reference; efficient in places but noticeably over-explained.	3 / 5
Actionability	The example usage is a complete, copy-paste-ready runnable pipeline (load → filter → fit → test → shrink → export → plot) with concrete imports, parameters, and contrast syntax covering the common treated-vs-control case.	5 / 5
Workflow Clarity	Steps are clearly numbered (1–6) with sample alignment and filtering safeguards, but there are no explicit validation checkpoints verifying results (e.g., sanity-checking counts orientation, confirming dds fitted) before downstream export, so a checkpoint is implicit rather than enforced.	4 / 5
Progressive Disclosure	Good structure with bundled references and a CLI script clearly signaled one level deep ('references/api_reference.md', 'references/workflow_guide.md', 'scripts/run_deseq2_analysis.py') all of which exist; minor gap is that some detail (e.g., the full volcano-plot code, dispersion pipeline) is inlined rather than deferred.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 high-quality description that concretely names the domain, the statistical workflow, and explicit trigger conditions in third person. It is specific, complete, and well-differentiated with only minor room to surface additional synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Wald tests, FDR correction, and optional LFC shrinkage' over 'condition/batch/covariate designs' — giving comprehensive, specific coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Differential gene expression analysis... using a DESeq2-like workflow in Python') and when ('use when you need Wald tests, FDR correction... for condition/batch/covariate designs') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('DESeq2-like', 'bulk RNA-seq', 'Wald tests', 'FDR correction', 'LFC shrinkage') that users would say, though it omits common synonyms like 'differential expression' and 'padj' that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (bulk RNA-seq DESeq2-style DE analysis in Python) with domain-specific triggers that are unlikely to collide with unrelated skills.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/pydeseq2/SKILL.md
Commit: 63c61d3

Reviewed: 10 hours 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.