tooluniverse-multi-omics-integration

Multi-omics integration — orchestrate per-layer analysis (transcriptomics, proteomics, epigenomics, genomics, metabolomics) then perform cross-omics correlation, multi-omics clustering, and pathway-level integration. Use for integrative systems-biology analysis, multi-modal disease characterization, and cross-omics biomarker discovery.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-multi-omics-integration/SKILL.md

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 useful tables and a clear 8-phase workflow, but it over-explains known biology, defers complete code to a non-existent phase_details.md, and lacks inline validation checkpoints. Addressing these would lift it from adequate to strong.

Suggestions

Trim or remove the 'Domain Reasoning' section — it explains biology concepts Claude already knows; keep only the actionable 'LOOK UP DON'T GUESS' guidance.

Add inline validation checkpoints between workflow phases (e.g., after Phase 2 assert common_samples >= 10; after Phase 4 flag genes with |r| below a computed threshold) rather than relying on a post-hoc 'Quantified Minimums' table.

Either ship phase_details.md as a bundle file or inline the complete correlation/clustering code — currently the body defers to phase_details.md, which does not exist, leaving code fragments incomplete.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and code, but the 'Domain Reasoning' section explains biology Claude already knows (concordant/discordant mRNA-protein, post-transcriptional regulation via miRNA/degradation), which is unnecessary padding.	2 / 3
Actionability	Provides some concrete code (match_samples_across_omics, a spearmanr loop) but several blocks are incomplete fragments, and complete implementations are deferred to a phase_details.md that is not present in the bundle.	2 / 3
Workflow Clarity	The 8 phases are clearly sequenced, but there are no inline validation checkpoints between phases; the 'Quantified Minimums' table is a post-hoc checklist rather than feedback loops, capping clarity at 2 for a batch analytical operation.	2 / 3
Progressive Disclosure	Sections are well-organized with clearly signaled one-level-deep references to phase_details.md, but that referenced file does not exist in the bundle, so the disclosure points to missing detail.	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: it states concrete multi-omics actions, gives an explicit 'Use for' trigger, uses natural domain terms, and occupies a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'orchestrate per-layer analysis (transcriptomics, proteomics, epigenomics, genomics, metabolomics)' and 'perform cross-omics correlation, multi-omics clustering, and pathway-level integration' — matching the level-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('orchestrate per-layer analysis... perform cross-omics correlation...') and when ('Use for integrative systems-biology analysis, multi-modal disease characterization, and cross-omics biomarker discovery'), matching the level-3 anchor with an explicit 'Use for' trigger clause.	3 / 3
Trigger Term Quality	Includes natural domain terms a user would actually say — 'multi-omics integration', 'cross-omics correlation', 'multi-omics clustering', 'biomarker discovery' — with good coverage rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear cross-omics integration niche with domain-specific triggers unlikely to fire for single-omics skills, and uses third-person voice throughout ('orchestrate', 'perform').	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-multi-omics-integration/SKILL.md
Commit: 089eb8e

Reviewed: about 9 hours 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.