tooluniverse-multiomic-disease-characterization

Comprehensive multi-omics disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers for systems-level understanding. Produces a detailed multi-omics report with quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses. Uses 80+ ToolUniverse tools across 8 analysis layers. Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification from a disease perspective.

Quality

88%

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

Quality

Content

77%

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

The body is highly actionable with clear, validated multi-phase workflows, but it is a token-heavy monolith that inlines reference material a leaner overview would split into separate files.

Suggestions

Move the full report template, 'Response Format Notes' JSON examples, and 'Tool Parameter Quick Reference' table into a references/ file (e.g. REPORT_TEMPLATE.md, TOOL_REFERENCE.md) and keep SKILL.md a concise overview with one-level-deep links.

Trim domain explanations Claude already knows (e.g. degree/betweenness centrality definitions, GO aspect descriptions) down to the operational guidance.

Consolidate the duplicated scoring tables ('Multi-Omics Confidence Score' appears three times: components, template, and Phase 7) into a single authoritative section.

Dimension	Reasoning	Score
Conciseness	Per-section guidance is efficient, but the body is a ~1130-line monolith that explains some domain concepts Claude already knows and inlines a full report template, response-format JSON, and a complete tool reference table that pad the token budget.	2 / 3
Actionability	Concrete tool names with exact required inputs, output schemas, required-parameter flags, copy-ready Python tracking dicts, and explicit confidence-score arithmetic give fully executable guidance.	3 / 3
Workflow Clarity	Eight numbered phases are sequenced with explicit workflows, completion checklists as validation checkpoints, and fallback/collision-aware error-recovery loops for fragile steps.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and everything lives inline; content that should be one level deep (report template, response examples, full tool reference) is bundled into the single SKILL.md.	2 / 3
	Total	10 / 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 third-person, specific, and complete with an explicit trigger clause covering natural user phrasings. It is somewhat verbose but not at the expense of clarity or distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions including 'quantitative confidence scoring (0-100), cross-layer gene concordance analysis, biomarker candidates, therapeutic opportunities, and mechanistic hypotheses', matching the top anchor.	3 / 3
Completeness	Explicitly answers both what it does (multi-omics characterization with a detailed report) and when to use it via an explicit 'Use when...' trigger clause.	3 / 3
Trigger Term Quality	The 'Use when users ask about disease mechanisms, multi-omics analysis, systems biology of disease, biomarker discovery, or therapeutic target identification' clause covers natural phrasings users would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche — multi-omics disease characterization from a disease perspective — with specific triggers unlikely to fire for sibling single-layer skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1139 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-multiomic-disease-characterization/SKILL.md
Commit: df37802

Reviewed: 2 days 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.