kegg-database
Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.
89
86%
Does it follow best practices?
Impact
93%
1.97xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its domain (KEGG REST API), lists specific capabilities, and provides explicit guidance on when to use it versus alternatives like bioservices. The description effectively differentiates itself and uses appropriate technical terminology that users in this domain would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (pathway analysis, gene-pathway mapping, etc.) AND when ('For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'KEGG', 'REST API', 'pathway analysis', 'metabolic pathways', 'drug interactions', 'ID conversion', 'HTTP/REST'. Good coverage of domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting KEGG database with REST API access. Explicitly distinguishes itself from bioservices for Python workflows, reducing conflict risk with similar bioinformatics skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability through concrete, executable Python examples and good progressive disclosure. The main weaknesses are moderate verbosity in introductory sections and missing validation/error-handling steps in the multi-step workflows, which is important when making sequential API calls that could fail.
Suggestions
Add validation checkpoints to workflows (e.g., 'Check if gene_results is empty before proceeding to Step 2')
Remove or condense the 'Overview' and 'When to Use This Skill' sections - Claude already knows what KEGG is from the skill description
Add error handling examples showing how to check HTTP status codes and handle empty results in workflow code
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., 'KEGG is a comprehensive bioinformatics resource' and 'When to Use This Skill' section). The workflow examples are thorough but could be more condensed. | 2 / 3 |
Actionability | Provides fully executable Python code examples with proper imports, specific function calls, and clear parameter usage. All code snippets are copy-paste ready with realistic examples like 'hsa:10458' and 'cpd:C00002'. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, but lack explicit validation checkpoints. No error handling or verification steps between API calls, which is important for batch operations and data integrity. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from Quick Start to Core Operations to Workflows. References to external files (scripts/kegg_api.py, references/kegg_reference.md) are clearly signaled and one level deep. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- Reviewed
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.