gsva-analysis-and-visualization

Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression, single-cell analysis, methylation analysis, clinical diagnosis.

Quality

92%

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

92%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 skill body is highly actionable and well-structured with clear workflow sequencing, validation checkpoints, and correctly signaled one-level-deep references. The only weakness is minor redundancy between the scope/guidance sections and the trailing Input Validation and Implementation Checklist sections.

Suggestions

Consolidate the 'Input Validation' acceptance list with the 'When to Use' bullets to avoid restating scope twice; keep the actionable validation (column names, missing-value rule) inline only.

Trim or remove the 'Implementation Checklist' section — it tracks authoring status rather than guiding execution and adds tokens Claude does not need.

Shorten the out-of-scope canned response block since the 'When Not to Use' section already enumerates the same exclusions.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and largely efficient, but the 'Input Validation' section and the out-of-scope response block partially restate 'When to Use'/'When Not to Use' guidance, and the 'Implementation Checklist' adds tracking prose that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready Rscript commands for analyze, visualize, and full modes, backed by a complete argument table, input-format examples, output-file tables, and error codes.	5 / 5
Workflow Clarity	A clearly sequenced three-step workflow (validate → pathway analysis → generate output) with explicit validation in Step 1 and a feedback loop via the Error Handling table (error → fix → rerun), plus visualize-mode preconditions and provenance preservation.	5 / 5
Progressive Disclosure	Clear overview with a 'When to Read External Files' table signaling one-level-deep references to references/algorithm.md, references/troubleshooting.md, references/cli-guide.md, and scripts/main.R, all of which exist; no nested references.	5 / 5
	Total	19 / 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.

The description is highly specific, complete, and distinctive, naming concrete actions, natural trigger keywords, and an explicit out-of-scope boundary. It is only slightly held back from full marks on trigger-term breadth by the absence of synonym/file-extension variants.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file' and 'generate a heatmap from the saved GSVA result object' — with comprehensive coverage of inputs and outputs.	5 / 5
Completeness	Explicitly answers both 'what' (run GSVA/ssGSEA differential analysis and generate a heatmap) and 'when' ('Use this skill to...', 'Trigger keywords:', and a 'NOT for' exclusion list) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage ('GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB') that users would actually say, but lacks the synonym/file-extension breadth (e.g. .rda, RNA-seq, enrichment score) that distinguishes the top anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche — bulk-expression pathway-level GSVA/ssGSEA plus heatmap — paired with an explicit 'NOT for' list (gene-level DE, single-cell, methylation, clinical diagnosis) that minimizes conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/gsva-analysis-and-visualization/SKILL.md
Commit: f5ef65b

Reviewed: ~11 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.