gsea

Run GSEA on a ranked gene list and produce the enrichment table, running-score table, and enrichment plots.

Quality

74%

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 ./awesome-med-research-skills/Data Analysis/gsea/SKILL.md

Quality

Content

82%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 and well-structured with strong progressive-disclosure signaling, held back only by a missing referenced test-data file and minor conciseness redundancy. Adding the absent sample data file and trimming the inline plot-argument table would push it to the top band.

Suggestions

Ship or remove the referenced tests/data/sample_deg_results.csv so the documented smoke-test command actually runs.

Move the large plot-mode argument table into references/cli-guide.md (or a dedicated args reference) and keep only the most-used flags inline.

Remove the 'Value constraints' subsection that duplicates type/species values already listed in the argument table, or replace it with a cross-reference.

Dimension	Reasoning	Score
Conciseness	The body is lean reference material (argument tables, commands, output specs) with no over-explanation of concepts Claude already knows; not a 5 because the value-constraints section repeats values already in the argument table and the 50+ flag plot-mode table is heavy inline token load.	4 / 5
Actionability	It provides copy-paste-ready Rscript commands for both analysis and plot modes, full argument tables with types and defaults, a sample input CSV, an output-file table, and a minimal test command with expected outputs and exit code, fully covering the common cases.	5 / 5
Workflow Clarity	Mode selection and precedence (plot mode wins) are clearly sequenced, and error codes, exit codes, plus a Testing section with expected outputs give a verification path, so the batch-operation cap does not apply; not a 5 because there is no explicit 'verify outputs / check exit code' checkpoint woven into the main usage workflow.	4 / 5
Progressive Disclosure	The 'When to read external files' table gives well-signaled one-level-deep references to real files (algorithm.md, cli-guide.md, troubleshooting.md, main.R); not a 5 because tests/data/sample_deg_results.csv is referenced multiple times but is missing from the bundle, and the large inline plot-mode argument table could live in a reference file.	4 / 5
	Total	17 / 20 Passed

Description

66%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 names concrete outputs, but it omits any 'Use when...' trigger guidance, which caps completeness and slightly weakens distinctiveness. Adding an explicit trigger clause would lift the two capped dimensions.

Suggestions

Add a 'Use when ...' clause naming natural triggers, e.g. 'Use when the user asks for gene set enrichment analysis on a ranked gene list, GSEA plots, or enrichment tables.'

Include common synonyms and file extensions (e.g. 'gene set enrichment analysis', '.csv') to broaden trigger-term coverage.

Briefly distinguish from adjacent methods (e.g. 'not for ssGSEA or over-representation analysis') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain (GSEA on a ranked gene list) plus three concrete outputs (enrichment table, running-score table, enrichment plots), matching the 'several specific actions; minor gaps' anchor; not a 5 because it omits the plot-from-existing-files mode and smoke-test scope.	4 / 5
Completeness	It clearly answers 'what' (run GSEA, produce tables and plots) but has no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	'GSEA', 'ranked gene list', and 'enrichment table/plots' are natural bioinformatics trigger terms with good coverage; not a 5 because it lacks the spelled-out 'gene set enrichment analysis' and file extensions (.csv) as synonyms.	4 / 5
Distinctiveness Conflict Risk	'Run GSEA on a ranked gene list' is a distinct niche with minimal conflict risk; not a 5 because the absence of an explicit trigger phrase leaves minor overlap risk with related enrichment skills (ssGSEA, over-representation analysis).	4 / 5
	Total	15 / 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/gsea/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.