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.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tooluniverse-multiomic-disease-characterization in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-organized, action-dense pipeline skill that sequences 9 omics phases and surfaces concrete tool-parameter pitfalls while pushing detail to reference files. It would reach the top tier by inlining a compact executable example and an explicit per-phase validation checkpoint.

Suggestions

Inline one small executable snippet (e.g., a Python block running a cross-layer concordance count) so the core analysis is copy-paste ready, not only described via tool-reference.md.

Add an explicit validation/checkpoint step to one or two fragile phases (e.g., verify Ensembl IDs resolve after Phase 1 before Phase 2 depends on them) to strengthen feedback loops.

Confirm the five referenced files (tool-reference.md, report-template.md, integration-scoring.md, response-formats.md, use-patterns.md) are present in the bundle so the one-level-deep references are materialized, not dangling.

DimensionReasoningScore

Conciseness

Largely lean — it assumes Claude knows what omics layers are and avoids padding, with a dense, useful KEY PRINCIPLES list and per-phase tool notes. A few enumerated principles and section transitions could be trimmed without loss, keeping it just below a 5.

4 / 5

Actionability

Names exact tools and pinpoints parameter pitfalls ('STRING protein_ids: must be array', 'ReactomeAnalysis newline-separated'), which is highly actionable. It is mostly executable guidance but defers full per-phase workflows and code to tool-reference.md rather than inlining them, leaving minor gaps.

4 / 5

Workflow Clarity

The 9-phase pipeline is clearly sequenced with 'ALWAYS FIRST' disambiguation and a report-first principle, plus a completeness checklist concept. It is not a destructive/batch operation, so no 3-cap applies, but explicit per-phase validation checkpoints are only implied rather than spelled out inline.

4 / 5

Progressive Disclosure

Good structure: SKILL.md is an overview with a clear reference-files table pointing one level deep to tool-reference.md, report-template.md, integration-scoring.md, and others, each with described contents. Minor gap: no references/scripts/assets bundle directories exist, so the split is documentary rather than materialized here.

4 / 5

Total

16

/

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 conveys both capability and explicit use triggers for a well-scoped multi-omics domain. It is slightly technical in its trigger phrasing but clearly distinguishes the skill from related tooluniverse skills.

DimensionReasoningScore

Specificity

Names the domain (genomics, transcriptomics, proteomics, pathways) and lists multiple concrete actions: 'characterization', 'Identifies therapeutic opportunities and biomarker candidates', 'integrating multi-layer molecular data' — comprehensive coverage.

5 / 5

Completeness

Clearly states what it does ('Comprehensive disease characterization...', 'Identifies...', 'integrating...') and gives an explicit 'Use for...' clause with concrete trigger phrases, answering both what and when.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('multi-omics', 'disease deep-dive reports', 'mechanism mapping', 'biomarker-and-target identification') but leans technical and misses plainer synonyms; good but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (multi-omics disease characterization) with domain-specific triggers; the broad 'comprehensive' framing is offset by the specific multi-layer omics scope, minimizing overlap with sibling skills.

5 / 5

Total

19

/

20

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.