go-kegg-enrichment
Performs GO (Gene Ontology) and KEGG pathway enrichment analysis on gene lists. Trigger when: - User provides a list of genes (symbols or IDs) and asks for enrichment analysis - User mentions "GO enrichment", "KEGG enrichment", "pathway analysis" - User wants to understand biological functions of gene sets - User provides differentially expressed genes (DEGs) and asks for interpretation - Input: gene list (file or inline), organism (human/mouse/rat), background gene set (optional) - Output: enriched terms, statistics, visualizations (barplot, dotplot, enrichment map)
82
82%
Does it follow best practices?
Impact
72%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
76%
14%Human Cancer Gene GO Enrichment Analysis
GO enrichment via gseapy pipeline
Uses gseapy library
100%
100%
Uses main.py script
0%
33%
Correct --genes argument
0%
37%
Human organism specified
50%
62%
GO analysis requested
62%
75%
Output directory set
62%
75%
Output directory created
50%
50%
GO result CSV files
100%
100%
Visualization files produced
100%
100%
REPORT.txt produced
50%
100%
analysis_notes.txt documents package
100%
100%
Without context: $0.3723 · 2m · 21 turns · 22 in / 6,621 out tokens
With context: $1.0430 · 3m 16s · 33 turns · 36 in / 11,068 out tokens
95%
18%Mouse Immune Response KEGG Pathway Analysis
KEGG pathway analysis with background gene set
Uses main.py script
0%
50%
Mouse organism specified
80%
100%
KEGG analysis selected
80%
100%
Background gene set provided
86%
100%
Background documented
100%
100%
Stringent q-value cutoff
90%
100%
Correct output directory
87%
100%
KEGG results CSV
50%
100%
Q-value cutoff documented
100%
100%
Significant pathways reported
100%
100%
Without context: $0.6121 · 2m 32s · 29 turns · 34 in / 7,588 out tokens
With context: $1.1004 · 3m 20s · 33 turns · 210 in / 9,645 out tokens
46%
-31%Quick GO Function Analysis for Neurodegeneration Genes
Enrichr API mode with selective GO ontologies
Uses Enrichr API flag
0%
0%
Online API documented
100%
100%
GO-only analysis
50%
0%
Selective ontologies
100%
0%
Custom p-value cutoff
80%
0%
P-value cutoff documented
100%
100%
Q-value cutoff documented
100%
100%
Ontologies documented
100%
100%
Output directory correct
87%
50%
Results per ontology reported
100%
100%
Without context: $0.2991 · 1m 23s · 19 turns · 23 in / 4,265 out tokens
With context: $0.9265 · 2m 54s · 35 turns · 246 in / 8,348 out tokens
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
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.