gokegg-analysis

Use when performing GO and KEGG enrichment on a gene list from bulk RNA-seq or microarray studies, then generating a combined GO/KEGG dot chart. NOT for single-cell RNA-seq, methylation data, or non-expression data.

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

78%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.

A highly actionable, well-structured CLI skill body with excellent progressive disclosure and strong validation/error-recovery guidance. The main weakness is redundancy across the example-command and separator sections, which inflates token cost without adding clarity.

Suggestions

Collapse the smoke-test, usage, and separator-example commands into a single representative example plus a compact separator-matrix table to remove near-duplicate command lines.

Move the long parameter table to references/cli-guide.md and keep only the required flags and one full example inline, relying on the existing 'When To Read External Files' table for navigation.

Promote the post-run checklist into an explicit numbered run-then-verify workflow so validation checkpoints are sequenced rather than only listed after the fact.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material with no padding of concepts Claude already knows, but it repeats near-identical example commands (usage vs. smoke test vs. separator examples) and the separator-examples block duplicates the Input Format section, so it could be tightened.	3 / 5
Actionability	Fully copy-paste-ready executable commands with a complete parameter table (types, defaults, required flags), output-file table, and error codes paired with fixes, covering the common cases comprehensively.	5 / 5
Workflow Clarity	The run-then-verify flow is supported by an explicit post-run checklist that validates outputs before claiming success and an error-code table providing recovery feedback, but validation is post-hoc rather than interleaved across a multi-step sequence, leaving minor gaps.	4 / 5
Progressive Disclosure	A 'When To Read External Files' table up front clearly signals one-level-deep references (algorithm.md, troubleshooting.md, cli-guide.md, main.R), all of which exist as real bundle files, with bulk detail appropriately split out of the overview.	5 / 5
	Total	17 / 20 Passed

Description

87%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 concise, well-targeted description that clearly states capability, trigger conditions, and exclusions in third-person imperative voice with no padding. Minor gains are available from adding pathway-analysis synonyms and one or two more concrete sub-actions.

Dimension	Reasoning	Score
Specificity	Names the domain (bulk RNA-seq/microarray) and two concrete actions ('performing GO and KEGG enrichment on a gene list' and 'generating a combined GO/KEGG dot chart') plus explicit negative scope, sitting just above the 1-2-action anchor but short of comprehensive multi-action coverage.	4 / 5
Completeness	Explicitly answers both what (GO/KEGG enrichment plus combined dot chart) and when via a concrete 'Use when performing ... from bulk RNA-seq or microarray studies' trigger, reinforced by an explicit 'NOT for ...' exclusion clause.	5 / 5
Trigger Term Quality	Strong natural terms a bioinformatician would say ('GO and KEGG enrichment', 'gene list', 'bulk RNA-seq', 'microarray', 'dot chart'), but common synonyms like 'pathway analysis' or 'over-representation analysis/ORA' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (GO/KEGG enrichment on gene lists from expression studies with dot-chart output) and the explicit negative scope (not single-cell, methylation, or non-expression data) sharply reduces overlap with adjacent skills.	5 / 5
	Total	18 / 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/gokegg/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.