tooluniverse-kegg-disease-drug

KEGG-based disease-drug-variant network research. Connects diseases to causal genes, drugs to molecular targets, and variants to pathways using KEGG's editorially curated databases (KEGG Disease, Drug, Network, Variant, Pathway). Use for drug repurposing via shared pathways, mechanistic disease-gene-drug networks, and pathway-based target discovery. Distinguishes direct (binding) vs indirect (pathway co-membership) drug-target relationships.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 body with executable code and a clear phased workflow, weakened by redundant restatement of the same caveats across two reasoning sections and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Deduplicate the direct-vs-indirect, KEGG-coverage, and ID-namespace caveats: state each once in 'Reasoning Strategy' and reference it from 'Interpretation Guidance' instead of restating.

Add explicit workflow checkpoints, e.g. 'if KEGG_search_disease returns no entries, broaden the keyword or fall back to Reactome/WikiPathways', to turn the sequence into a feedback loop.

Move the evidence-grading table and interpretation-guidance bullets into a references/ file (e.g. INTERPRETATION.md) and link to it from SKILL.md to apply progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but the direct-vs-indirect distinction, KEGG-coverage caveat, and ID-namespace caveat are each restated across 'Reasoning Strategy' and 'Reasoning Framework / Interpretation Guidance', which could be tightened.	2 / 3
Actionability	Provides executable Python for every phase plus a full end-to-end example and concrete ID-conversion/link calls, matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	Phases are clearly sequenced (Phase 1 -> 5 -> Report) and an evidence-grading table offers a validation lens, but the workflow steps lack explicit error-recovery checkpoints (e.g., what to do when a disease search or ID conversion returns nothing).	2 / 3
Progressive Disclosure	Well-sectioned but monolithic at ~190 lines with no bundle files (references/scripts/assets are empty); content like the evidence-grading and interpretation-guidance sections is inline where a one-level-deep reference file would reduce top-level tokens.	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 description: concrete actions, explicit 'Use for' triggers, named databases, and a distinctive direct/indirect framing. Third-person voice is maintained throughout with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Connects diseases to causal genes, drugs to molecular targets, and variants to pathways' and 'Distinguishes direct (binding) vs indirect (pathway co-membership) drug-target relationships' — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Connects diseases to causal genes, drugs to molecular targets...') and when via an explicit 'Use for drug repurposing via shared pathways...' clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Includes natural domain terms a user would say — 'KEGG', 'drug repurposing', 'disease-gene-drug networks', 'target discovery' — giving good coverage rather than just technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to KEGG's named curated databases with a distinctive direct-vs-indirect framing, giving it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-kegg-disease-drug/SKILL.md
Commit: 089eb8e

Reviewed: about 8 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.