CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

50%

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 concrete quantified thresholds and a clear phased pipeline, but it suffers from redundancy between the workflow diagram and phase summaries, missing inline executable code, absent error-recovery feedback loops, and dangling references to bundle files that are not present.

Suggestions

Merge the ASCII Workflow Overview with the Phase Summaries into a single representation to remove the duplicated per-phase descriptions and improve conciseness.

Add explicit feedback loops for QC/batch failures (e.g., 'if CV >30% in QC samples, re-run calibration or exclude the batch') to raise workflow clarity.

Either inline a minimal executable Python snippet for key phases or create the referenced code_examples.md and report_template.md files so the progressive-disclosure references resolve to real bundle files.

DimensionReasoningScore

Conciseness

The ASCII Workflow Overview diagram and the subsequent Phase Summaries restate the same per-phase content, and the Domain Reasoning section explains normalization/batch-effect concepts Claude largely already knows; mostly efficient but could be tightened by merging the two.

2 / 3

Actionability

Concrete thresholds are given (CV <30%, blank >3x, ±5 ppm, adj p<0.05, |log2FC|>1.0), but no executable code is inline and the referenced code_examples.md does not exist, leaving guidance specific but incomplete.

2 / 3

Workflow Clarity

The 8-phase pipeline is clearly sequenced with embedded QC validation criteria (Phase 2), but there are no explicit feedback/error-recovery loops describing what to do when a QC gate fails, and batch correction lacks a verification checkpoint.

2 / 3

Progressive Disclosure

Sections are organized and a one-level-deep 'Reference Files' section signals report_template.md and code_examples.md, but those files (and any references/scripts/assets bundles) do not exist, so the references are dangling rather than backed by an actual bundle structure.

2 / 3

Total

8

/

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.

The description is strong: concrete actions, explicit trigger clause, third-person voice, and a distinct metabolomics niche with minimal conflict risk. No significant weaknesses to address.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'metabolite identification, quantification (TIC normalization, batch correction), differential analysis, and pathway interpretation' — matching the multi-action anchor.

3 / 3

Completeness

Explicitly answers both what ('Analyze metabolomics data end-to-end...') and when ('Use for processing mass-spec metabolomics output...'), with an explicit 'Use for' trigger clause.

3 / 3

Trigger Term Quality

Natural user-facing terms like 'mass-spec metabolomics output', 'normalization choice', 'untargeted metabolomics workflows', and 'integrating with other omics layers' cover common phrasings a user would say.

3 / 3

Distinctiveness Conflict Risk

Metabolomics is a clearly delineated niche with distinct triggers, unlikely to conflict with adjacent omics skills; voice is third person ('Analyze', 'Use for').

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.