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.

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with executable code and concrete workflows, but the body is verbose — duplicating reference material inline and omitting explicit response-validation checkpoints in its batch/API workflows. Tightening the inline duplication and adding validate-before-parse steps would lift the weaker dimensions.

Suggestions

Remove the pathway-categories, identifier-formats, and API-limitations sections from SKILL.md and point to references/kegg_reference.md instead, keeping only the overview and quick-start inline.

Add an explicit validation step in each workflow that checks for the 'Error:' prefix returned by the helpers on HTTPError before parsing the response with .split('\n').

Cut the definitional opening ('KEGG ... is a comprehensive bioinformatics resource ...') since Claude already knows what KEGG is.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense, earning-their-place code examples, but it repeats material already in the reference (pathway categories, identifier formats, API limitations) and opens with concept text Claude already knows ('KEGG ... is a comprehensive bioinformatics resource'); not a 1 because it is not padded throughout, not a 3 because of the real duplication against references/kegg_reference.md.	2 / 3
Actionability	Provides fully executable Python with real imports and concrete IDs ('hsa:10458', 'hsa00010', 'cpd:C00002') plus five copy-paste-ready workflows; not a 2 because the guidance is complete and specific rather than pseudocode or abstract.	3 / 3
Workflow Clarity	Five workflows are clearly numbered, but they parse responses with .split('\n') without checking the 'Error:' strings the helpers return on HTTPError, so validation checkpoints for these batch/API operations are missing or implicit; not a 1 because sequencing is clear, capped at 2 (not 3) because explicit validate-then-proceed feedback loops are absent.	2 / 3
Progressive Disclosure	SKILL.md clearly signals verified one-level-deep references (references/kegg_reference.md, scripts/kegg_api.py) with easy navigation, but substantial reference content (pathway categories, identifiers, limitations) is duplicated inline rather than split out; not a 1 because references are real and well-signaled, not a 3 because content that should live only in the reference is repeated inline.	2 / 3
	Total	9 / 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.

A strong, third-person description that states concrete capabilities, supplies explicit use-when triggers, and actively disambiguates from a competing tool. All four dimensions hit the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion' — matching the anchor for several specific concrete actions; not a 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ('Direct REST API access to KEGG... pathway analysis... ID conversion') and when ('Use this for direct HTTP/REST work or KEGG-specific control'); not a 2 because the trigger guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Covers natural domain terms a user would say — 'KEGG', 'REST API', 'pathway analysis', 'drug interactions', 'ID conversion', 'HTTP/REST', 'KEGG-specific control' — matching the good-coverage anchor; not a 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear KEGG-specific niche and even disambiguates against a sibling ('For Python workflows with multiple databases, prefer bioservices'), making wrong-skill triggering unlikely; not a 2 because the scope is sharply bounded.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/databases/kegg-database/SKILL.md
Commit: 52845c3

Reviewed: about 12 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.