tooluniverse-rnaseq-deseq2

RNA-seq differential expression analysis with DESeq2, edgeR, and limma-voom — DEG lists, fold changes, dispersion estimation, design formulas including covariates, multi-condition contrasts, and Venn-set operations across groups. Routes across DESeq2 (default), edgeR (QL-F / exact test for small replicate counts), and limma-voom (large n / complex designs). Use when you have a count matrix + metadata, want to find DEGs, or need dispersion/PCA/clustering analysis. Includes RULE ZERO precedence (read executed.ipynb if present).

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%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 executable wrappers and well-designed decision tables, and its validation discipline is strong. Its main weaknesses are visible redundancy across overlapping sections and two dangling reference links plus inlined material that would suit separate files.

Suggestions

Remove the two missing reference links (design_formula_guide.md and r_clusterprofiler_guide.md) or create the files so navigation is not broken.

Consolidate the repeated R-vs-pydeseq2 and set-operation/Venn-denominator guidance into a single authoritative section instead of restating it across 'CRITICAL', 'LOOK UP DON'T GUESS', and 'Analysis conventions'.

Move the inlined decision tables and calculation conventions (e.g., density/per-chromosome, strain-identity pinning) into reference files to slim SKILL.md toward an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with genuinely non-obvious domain gotchas, but the same guidance recurs across multiple sections (R-vs-pydeseq2 choice in 'CRITICAL', 'Analysis conventions', and 'R DESeq2 vs pydeseq2'; Venn denominators and set operations repeated in both the numbered rules and 'Analysis conventions'), which is padding Claude does not need twice.	3 / 5
Actionability	Copy-paste-ready bash, python, and R commands with full arguments, shown output formats, and decision tables mapping question phrasing to the exact script line to read — fully executable across the common cases.	5 / 5
Workflow Clarity	A clear sequenced primary-scripts-first flow with explicit validation checkpoints (read executed notebook first, match filters and outlier exclusions exactly, workspace isolation), but the repetition across sections slightly muddies which path is canonical, keeping it just below 5.	4 / 5
Progressive Disclosure	References are one level deep and gathered in a Reference Files section, but two links point to files that do not exist (design_formula_guide.md and r_clusterprofiler_guide.md), and substantial decision-table/convention content that belongs in references is inlined directly in SKILL.md rather than split out.	3 / 5
	Total	15 / 20 Passed

Description

100%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 third-person, specific, and trigger-rich, clearly stating both what the skill does and when to use it with concrete data-shape triggers. It is a strong example of a complete, distinctive skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'DEG lists, fold changes, dispersion estimation, design formulas including covariates, multi-condition contrasts, and Venn-set operations' — plus explicit routing rules across three frameworks, which is comprehensive coverage rather than 1-2 actions.	5 / 5
Completeness	Explicitly answers both: the 'what' (full capability list and routing logic) and the 'when' via 'Use when you have a count matrix + metadata, want to find DEGs, or need dispersion/PCA/clustering analysis', matching the anchor's what+when requirement.	5 / 5
Trigger Term Quality	Comprehensive natural terms a user would actually say: 'RNA-seq', 'differential expression', 'DESeq2', 'DEGs', 'count matrix', 'metadata', 'fold changes', 'dispersion', 'PCA', 'clustering', plus the framework names edgeR and limma-voom.	5 / 5
Distinctiveness Conflict Risk	A clear niche — RNA-seq DE analysis with named tools and data-shape triggers ('count matrix + metadata') — that would not fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (510 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 4 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-rnaseq-deseq2/SKILL.md
Commit: 1b02920

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.