CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 with executable examples and clear operation-by-operation guidance, but it loses points for missing validation checkpoints in batch workflows and — most seriously — for referencing bundle files (scripts/kegg_api.py, references/kegg_reference.md) that are not present in the skill bundle.

Suggestions

Add the missing bundle files: create `scripts/kegg_api.py` and `references/kegg_reference.md` so the core references the body relies on actually exist.

Insert explicit validation/retry checkpoints into the batch workflows (e.g., check HTTP 200 status, handle empty/404 results, retry on 400) to earn full workflow-clarity credit for risky operations.

Trim redundant KEGG domain exposition (Overview, Pathway Categories narrative) and condense the K-Dense Web promotion paragraph to respect the token budget.

DimensionReasoningScore

Conciseness

Mostly efficient with copy-paste-ready code blocks, but sections like the Overview and Pathway Categories repeat KEGG domain knowledge Claude likely already knows, and the K-Dense Web promotion paragraph adds off-skill prose that could be tightened.

2 / 3

Actionability

Provides fully executable, import-ready Python snippets for every core operation and four end-to-end workflows with concrete IDs and parameters, beyond the actionability anchor.

3 / 3

Workflow Clarity

Workflows are clearly sequenced into numbered steps, but batch/API operations have no validation or error-recovery checkpoints — only an after-the-fact Troubleshooting section — which per the rubric caps risky multi-step operations at 2.

2 / 3

Progressive Disclosure

The body repeatedly references `scripts/kegg_api.py` and `references/kegg_reference.md` as core materials, but neither the `scripts/` nor `references/` directories exist in the bundle, so the supposed one-level-deep references are dangling and navigation is broken.

1 / 3

Total

8

/

12

Passed

Description

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.

The description is specific, trigger-rich, complete, and well-differentiated, with an explicit 'Use this' clause and a helpful boundary against the bioservices skill. It is concise and uses appropriate third-person, capability-focused phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion') plus 'Direct REST API access to KEGG', matching the highest specificity anchor.

3 / 3

Completeness

Explicitly answers both what (REST API access with the listed operations) and when ('Use this for direct HTTP/REST work or KEGG-specific control'), with a clear guidance clause.

3 / 3

Trigger Term Quality

Good coverage of natural terms a user would say — 'KEGG', 'Pathway analysis', 'gene-pathway mapping', 'metabolic pathways', 'drug interactions', 'ID conversion', 'HTTP/REST', 'Python workflows'.

3 / 3

Distinctiveness Conflict Risk

Clear niche (KEGG REST API) with a disambiguating handoff ('For Python workflows with multiple databases, prefer bioservices'), making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.