tooluniverse-lipidomics

Lipid analysis and lipid-disease associations using LIPID MAPS classification, HMDB metabolite data, KEGG/Reactome lipid pathways (sphingolipid, eicosanoid, steroid, fatty acid), and PubChem chemical info. Use for lipid identification, lipid metabolism pathway mapping, and lipid-associated disease analysis (cardiovascular, diabetes, NAFLD).

Quality

88%

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

77%

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

A well-structured, actionable lipidomics pipeline with concrete tool calls, a clear phased workflow, and error-recovery guidance. Its main weaknesses are a verbose conceptual opening and a monolithic single-file layout where large reference tables could be split out.

Suggestions

Tighten the 'Reasoning Strategy' paragraph by trimming biological explanations Claude already knows; keep the specific m/z values, KEGG IDs, and enzyme-disease mappings that earn their tokens.

Move the 8-row KEGG pathway table and the disease-context reference material into a references/ file (e.g., PATHWAYS.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit validation gate in Phase 4 (e.g., assert changed-lipid categories resolve to LIPID MAPS IDs before enrichment) so the batch analysis has a clear validate→fix→retry checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain reference, but the opening 'Reasoning Strategy' paragraph explains biology concepts (m/z fragments, category-to-context mappings) at length that could be tightened.	2 / 3
Actionability	Provides executable tool calls with concrete parameters (e.g., LipidMaps_search_by_name(query="ceramide")) and a runnable pandas/scipy enrichment script that is copy-paste ready.	3 / 3
Workflow Clarity	The Phase 0–4 pipeline is clearly sequenced with a diagram, and Phase 0 includes explicit error-recovery feedback loops (search fails → try PubChem; species abbreviations return 0 results → use generic class name).	3 / 3
Progressive Disclosure	Well-sectioned single file, but ~170 lines with a large inline 8-row pathway reference table and no external reference files to split detailed material into.	2 / 3
	Total	10 / 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 precise, third-person description that states concrete capabilities, names the underlying data sources, and provides an explicit 'Use for' trigger clause covering the main use cases. It is clearly distinguishable from adjacent metabolomics and ADMET skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('lipid identification', 'lipid metabolism pathway mapping', 'lipid-associated disease analysis') and names specific data sources (LIPID MAPS, HMDB, KEGG/Reactome, PubChem).	3 / 3
Completeness	Clearly answers both what (lipid analysis via named classification/data sources) and when via an explicit 'Use for' trigger clause.	3 / 3
Trigger Term Quality	The 'Use for...' clause gives natural domain terms a user would say — lipid identification, pathway mapping, and disease analysis with concrete disease names (cardiovascular, diabetes, NAFLD).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear lipidomics niche with distinctive data sources and disease categories; unlikely to fire for general metabolomics or ADMET 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-lipidomics/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.