tooluniverse-metabolomics-pathway

Metabolomics pathway analysis — metabolite identification (HMDB, KEGG, ChEBI), pathway mapping (Reactome, KEGG, MetaCyc), disease associations, enzyme/gene linkage. Use for metabolite-to-pathway-to-disease connections, BridgeDb-based ID conversion, and integrating metabolomics with gene-level pathway analyses.

Quality

96%

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

92%

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

A dense, highly actionable single-file skill with a clear phased workflow, strong guardrails, and a useful corrections/fallback apparatus. Its main weakness is structure: the substantial inline tool catalog would benefit from progressive disclosure into a separate reference file rather than living entirely in SKILL.md.

Suggestions

Move the per-phase tool signature catalogs (Phases 0–5) into a references/REFERENCE.md, keeping SKILL.md as an overview that links one level deep to it — this would lift progressive_disclosure to 3.

Add a short 'Quick start' example at the top showing one end-to-end metabolite→pathway→disease lookup with actual tool calls, so the workflow is immediately graspable before the detailed reference.

Consider a compact decision table mapping common user goals (e.g. 'disease association for a metabolite', 'ID conversion') to the recommended first tool, reducing the need to scan all phases.

Dimension	Reasoning	Score
Conciseness	Lean reference of tool signatures, parameters, and ID examples with no padding or explanation of concepts Claude already knows; the 'Domain Reasoning' section adds only non-obvious domain knowledge (BridgeDb conversion, isomer identity pitfalls).	3 / 3
Actionability	Provides concrete, copy-ready guidance — specific tool names with REQUIRED params, real ID examples ('HMDB0000122', 'C00031', 'hsa:5230'), exact URL patterns ('moverz/REFMET/{mz}/{adduct}/{tolerance}'), and a corrections table; actionable for an instruction/tool-orchestration skill even without standalone Python code.	3 / 3
Workflow Clarity	Clear Phase 0→5→Report sequence with guardrails ('Always verify metabolite identity first', LOOK UP DON'T GUESS) and explicit fallback strategies for error recovery; this is analysis rather than destructive/batch work, so the verification-first emphasis suffices.	3 / 3
Progressive Disclosure	Well-organized into labeled phases, but the body is essentially a long inline catalog of tool signatures (Phases 0–5) with no bundle files; much of this reference material could live in a separate REFERENCE file rather than inline, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	11 / 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 names concrete capabilities, specific databases, and explicit 'Use for' triggers, making both scope and activation conditions unambiguous. It is concise without padding and clearly distinguishable from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'metabolite identification (HMDB, KEGG, ChEBI)', 'pathway mapping (Reactome, KEGG, MetaCyc)', 'disease associations', 'enzyme/gene linkage' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the four action categories) and when via a clear 'Use for metabolite-to-pathway-to-disease connections...' trigger clause, satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Covers natural domain terms a metabolomics user would say — 'metabolomics pathway analysis', 'metabolite-to-pathway-to-disease connections', 'BridgeDb-based ID conversion' — with good coverage of relevant variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (metabolomics pathway analysis) with distinct, specialized triggers unlikely to conflict with generic data or document skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-metabolomics-pathway/SKILL.md
Commit: 089eb8e

Reviewed: about 7 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.