CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-multiomic-disease-characterization

Comprehensive disease characterization across genomics, transcriptomics, proteomics, and pathways for systems-level understanding. Identifies therapeutic opportunities and biomarker candidates by integrating multi-layer molecular data. Use for full-omics disease deep-dive reports, mechanism mapping, and biomarker-and-target identification from multi-omics data.

63

Quality

73%

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-multiomic-disease-characterization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A well-sequenced, operationally dense pipeline body with strong tool-parameter guidance, weakened by conceptual restatement, absent executable code examples, and reference files that are signaled but missing from the bundle.

Suggestions

Provide at least one concrete Python snippet (e.g., a pandas/scipy concordance or confidence-score computation) to back the 'COMPUTE, DON'T DESCRIBE' directive instead of only describing it.

Ship the referenced bundle files (tool-reference.md, report-template.md, integration-scoring.md, response-formats.md, use-patterns.md) or inline their essential parts so signaled navigation actually resolves.

Trim the 13-item KEY PRINCIPLES list and the conceptual intro paragraph, which overlap with the phase-by-phase workflow, to recover token budget.

DimensionReasoningScore

Conciseness

Mostly operational and dense (tool names, parameter pitfalls, phases), but the conceptual intro paragraph and the 13-item KEY PRINCIPLES list partly restate the phase descriptions and could be tightened.

2 / 3

Actionability

Concrete tool names and specific parameter gotchas ('STRING protein_ids: must be array', 'ReactomeAnalysis identifiers are newline-separated') are actionable, but despite a 'COMPUTE, DON'T DESCRIBE' directive to write Python, no executable code examples are given and key workflows are deferred to reference files.

2 / 3

Workflow Clarity

The 9 phases (0-8) are clearly sequenced with explicit ordering markers ('ALWAYS FIRST', 'CRITICAL'), and a mandatory completeness checklist plus confidence-score finalization provide validation checkpoints for the multi-step process.

3 / 3

Progressive Disclosure

The Reference Files table signals one-level-deep references with clear per-file descriptions, but none of the five referenced files (tool-reference.md, report-template.md, integration-scoring.md, response-formats.md, use-patterns.md) actually exist in the bundle, breaking navigation.

2 / 3

Total

9

/

12

Passed

Description

85%

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 clearly states capabilities and explicit use triggers with a well-scoped niche. The main weakness is slightly technical trigger phrasing rather than natural user terms.

Suggestions

Soften 'full-omics disease deep-dive reports' toward phrasings users actually say, e.g. 'Use when the user asks for a multi-omics deep dive on a disease, wants cross-layer concordance, or needs biomarker/druggable-target discovery.'

DimensionReasoningScore

Specificity

Names concrete actions across multiple omics layers — 'disease characterization across genomics, transcriptomics, proteomics, and pathways', 'Identifies therapeutic opportunities and biomarker candidates by integrating multi-layer molecular data' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (multi-layer disease characterization, therapeutic/biomarker identification) and when via an explicit 'Use for full-omics disease deep-dive reports, mechanism mapping...' trigger clause.

3 / 3

Trigger Term Quality

The 'Use for' clause surfaces relevant terms ('multi-omics', 'biomarker-and-target identification', 'mechanism mapping'), but phrasing like 'full-omics disease deep-dive reports' is somewhat jargon-heavy and misses common natural variations a user might say.

2 / 3

Distinctiveness Conflict Risk

The multi-omics / full-omics disease deep-dive niche is clearly scoped with distinct triggers, making it unlikely to fire for the single-layer sibling skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.