tooluniverse-metabolomics-analysis

Analyze metabolomics data end-to-end — metabolite identification, quantification (TIC normalization, batch correction), differential analysis, and pathway interpretation. Use for processing mass-spec metabolomics output, normalization choice, untargeted metabolomics workflows, and integrating with other omics layers.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-metabolomics-analysis/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

The body is well-structured with a clear eight-phase workflow and concrete analytical thresholds, but it is somewhat redundant and over-explains familiar concepts, and its two reference files are missing from the bundle, breaking progressive disclosure.

Suggestions

Provide the missing code_examples.md and report_template.md bundle files (or remove the references), since the body currently points to non-existent files.

Trim the 'Domain Reasonation' section to skill-specific guidance only and remove the overlap between the ASCII Workflow Overview and the Phase Summaries.

Add explicit validate→fix→retry feedback loops for batch-effect correction and QC failures, since this is a batch analytical workflow.

Dimension	Reasoning	Score
Conciseness	Mostly information-dense, but the 'Domain Reasoning' section over-explains normalization concepts Claude already knows, and the eight-phase ASCII workflow overlaps materially with the subsequent Phase Summaries, so it could be tightened.	3 / 5
Actionability	Provides concrete, executable specifications — CV <30%, blank >3x, adj p<0.05, \|log2FC\|>1, confidence levels L1–L4, recommended PQN normalization — though all runnable code is externalized to code_examples.md rather than shown inline.	4 / 5
Workflow Clarity	The eight-phase sequence is clearly laid out with gating QC criteria (reject >30% CV, keep >3x blank, internal-standard recovery 95–105%) acting as validation checkpoints, though explicit validate→fix→retry feedback loops for batch failures are not spelled out.	4 / 5
Progressive Disclosure	Structure is sound and references are clearly signaled one level deep (code_examples.md, report_template.md), but neither referenced file exists in the bundle, so the navigation leads to dead ends — a real organization gap rather than a minor one.	3 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

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, specific description that clearly states what the skill does and when to use it, with concrete sub-actions and a distinct metabolomics niche. The only gap is missing common platform synonyms and file extensions in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with sub-actions — 'metabolite identification', 'quantification (TIC normalization, batch correction)', 'differential analysis', 'pathway interpretation' — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (end-to-end metabolomics analysis with named sub-tasks) and 'when' ('Use for processing mass-spec metabolomics output, normalization choice, untargeted metabolomics workflows, and integrating with other omics layers').	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('metabolomics data', 'untargeted metabolomics workflows', 'integrating with other omics layers') but omits common platform synonyms and file extensions (LC-MS, GC-MS, NMR, .mzML) that users frequently mention.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear metabolomics niche with distinct triggers; the only mild overlap is 'integrating with other omics layers', which is clearly subordinate to the metabolomics focus and unlikely to misroute.	5 / 5
	Total	19 / 20 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-metabolomics-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.