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.

61

Quality

72%

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

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

61%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 an efficient, well-organized overview with genuinely useful tool-parameter specifics and a clear 9-phase sequence. Its main weaknesses are missing validation feedback loops between phases and, most seriously, a progressive-disclosure scheme that points to five reference files which do not exist in the bundle.

Suggestions

Ship the five referenced files (tool-reference.md, report-template.md, integration-scoring.md, response-formats.md, use-patterns.md) in the bundle, or inline their essential content into SKILL.md so the overview's promises are reachable.

Add explicit validation checkpoints between phases (e.g. after disease disambiguation and after each omics layer) with a validate->fix->retry loop, rather than deferring all verification to Phase 8.

Include at least one concrete executable example (a sample tool call or a Python analysis snippet) in the body to back up the 'COMPUTE, DON'T DESCRIBE' directive, instead of relying solely on the missing tool-reference.md.

DimensionReasoningScore

Conciseness

Dense with non-obvious domain specifics (exact tool names, parameter formats, required fields) that Claude does not already know; only minor framing paragraphs ('Multi-omics disease characterization asks...') and the 13-item principles list could be trimmed.

4 / 5

Actionability

Provides concrete, executable-level guidance such as 'STRING protein_ids: must be an array' and 'ReactomeAnalysis identifiers are newline-separated', but includes no complete code examples and defers full parameter details to tool-reference.md, which is a minor gap.

4 / 5

Workflow Clarity

The 9 phases (Phase 0-8) are clearly sequenced, but validation exists only implicitly and at the final phase; for a multi-phase batch/database-query pipeline, the missing intermediate validate->fix->retry checkpoints cap this at 3 per the batch-operations guideline.

3 / 5

Progressive Disclosure

The body is well structured as an overview and clearly signals 5 reference files in a table, but none of those files (tool-reference.md, report-template.md, integration-scoring.md, response-formats.md, use-patterns.md) exist in the bundle, so the promised detailed content is unreachable and the disclosure scheme is broken.

2 / 5

Total

13

/

20

Passed

Description

83%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, well-structured description that clearly states capabilities and gives explicit 'Use for...' trigger guidance in the correct third-person voice. It is specific and largely distinct, with only minor gaps in natural trigger-term variations and slight overlap risk with adjacent disease skills.

DimensionReasoningScore

Specificity

Lists several concrete actions (characterize across four omics layers, 'Identifies therapeutic opportunities and biomarker candidates', 'integrating multi-layer molecular data') but the verbs are slightly more abstract than the anchor-5 examples, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both 'what' (multi-layer characterization, target/biomarker identification, data integration) and 'when' ('Use for full-omics disease deep-dive reports, mechanism mapping, and biomarker-and-target identification from multi-omics data') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage (genomics, transcriptomics, proteomics, pathways, biomarker, therapeutic, multi-omics) plus a 'Use for...' trigger clause, but it omits common natural variations a user might say (e.g. 'what genes are involved', 'disease mechanisms').

4 / 5

Distinctiveness Conflict Risk

Carves a clear multi-omics integration niche, but 'pathways' and general disease framing carry minor overlap risk with the closely related tooluniverse-disease-research and tooluniverse-systems-biology skills.

4 / 5

Total

17

/

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.