pydeseq2

Differential gene expression analysis for bulk RNA-seq with PyDESeq2, including formulaic designs, Wald tests, FDR correction, LFC shrinkage, and result visualization.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/pydeseq2/SKILL.md

Quality

Content

80%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 content is highly actionable and well-structured with a clean overview pointing to one-level-deep reference files, but the main batch workflow lacks explicit validation checkpoints, which limits workflow clarity.

Suggestions

Insert an explicit validation checkpoint in the Quick Start / core workflow (e.g., after deseqq2() and after ds.summary(), check size factors and p-value distribution before interpreting results) so the feedback loop is in the main flow rather than only in troubleshooting.

Consider moving the full volcano/MA plot code into a reference or a visualization section of the workflow guide to reduce inline bulk while keeping a minimal example in SKILL.md.

Add a short pre-flight validation step (index alignment between counts and metadata, non-zero counts) before fitting, mirroring the troubleshooting guidance proactively.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence (no concept over-explanation), with lean Quick Start and Key Reminders sections; minor trimming is possible in the inline visualization and troubleshooting code blocks, keeping it just below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready Quick Start, a real CLI script with exact arguments, concrete interpretation/visualization snippets, and an explicitly specified contrast format covering the common cases.	5 / 5
Workflow Clarity	A clear six-step sequence and Key Reminders are present, but the main workflow runs straight through without explicit validation checkpoints between steps; since this is a batch analysis operation, the missing inline validate/proceed feedback loop caps the score at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview that signals one-level-deep references (core_workflow_steps.md, analysis_patterns.md, api_reference.md, workflow_guide.md) and a script, each with an explicit 'use when' purpose, and the bundle files contain no nested .md references.	5 / 5
	Total	17 / 20 Passed

Description

62%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.

The description is specific and clearly distinct, naming PyDESeq2 and the key analysis techniques, but it omits any explicit 'when to use' trigger guidance, which limits its completeness and trigger-term coverage.

Suggestions

Add a 'Use when...' clause naming natural user phrases such as 'when the user mentions DESeq2, RNA-seq differential expression, or PyDESeq2' to satisfy the completeness 'when' requirement.

Broaden trigger-term coverage to include common synonyms and variants a user might say ('RNA-seq analysis', 'DESeq2', 'differential expression').

Keep the current tool-specific framing but ensure the description reads as a standalone statement that tells Claude both what it does and when to fire.

Dimension	Reasoning	Score
Specificity	Names the domain ('Differential gene expression analysis for bulk RNA-seq with PyDESeq2') plus several concrete sub-techniques ('Wald tests, FDR correction, LFC shrinkage, and result visualization'), with only minor coverage gaps; not a 5 because the listed items are components of one analysis rather than multiple distinct top-level actions.	4 / 5
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent trigger guidance for when Claude should invoke it, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords are present ('bulk RNA-seq', 'differential gene expression', 'PyDESeq2') but common natural variants a user would say ('RNA-seq analysis', 'DESeq2', 'differential expression analysis') are only partially covered, missing the breadth of the anchor-4 example.	3 / 5
Distinctiveness Conflict Risk	It targets a clear niche — PyDESeq2-based bulk RNA-seq differential expression — with distinct, tool-specific triggers and minimal overlap with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pydeseq2/SKILL.md
Commit: 36d8f13

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.