Name: tooluniverse-disease-research
Rating: 66.4 (1 reviews)
Author: mims-harvard

tooluniverse-disease-research

Generate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing candidates), clinical trials, epidemiology (prevalence, incidence), and phenotypes (HPO). Use for full disease overviews, comprehensive disease characterization, and orphan/rare-disease profiling.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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

Quality

Content

71%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 content is well-organized and actionable with concrete tools and a clear report-first workflow, but its progressive disclosure is fundamentally undermined because every referenced bundle file is missing. Supplying the referenced files would raise the progressive_disclosure score substantially.

Suggestions

Create the five referenced files (REPORT_TEMPLATE.md, RESEARCH_PROTOCOL.md, tool_usage_details.md, TOOLS_REFERENCE.md, EXAMPLES.md) so the body's pointers resolve, or inline the essential content and remove the dangling links.

Add explicit validation checkpoints to the report-first workflow (e.g., verify the report file was written, retry on tool error) to support the iterative batch-writing process.

Remove the broken cross-skill reference (skills/tooluniverse-rare-disease-diagnosis/scripts/clinical_patterns.py) or correct the path, since it currently points to a nonexistent script.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no over-explanation of basic concepts), with a few sections like 'LOOK UP, DON'T GUESS' that restate philosophy Claude already applies, keeping it just below the 5-anchor lean baseline.	4 / 5
Actionability	Provides concrete tool names, a 10-dimension mapping table, and one fully executable ZOOMA Python snippet, but the bulk of the per-section tool calls are deferred to a referenced file that does not exist, leaving minor gaps versus copy-paste-ready coverage.	4 / 5
Workflow Clarity	Clear report-first sequence and progressive-update pattern with an end-of-run quality checklist, but it lacks explicit in-process validation/error-recovery checkpoints for the iterative file-writing batch operation, capping it just below 5.	4 / 5
Progressive Disclosure	The body references REPORT_TEMPLATE.md, RESEARCH_PROTOCOL.md, tool_usage_details.md, TOOLS_REFERENCE.md, EXAMPLES.md and a cross-skill script, but none of these files exist in the bundle, so navigation breaks despite the references being clearly signaled.	2 / 5
	Total	14 / 20 Passed

Description

90%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.

The description is strong: third-person voice, concrete actions across named domains, and an explicit 'Use for...' trigger clause. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and domains — 'Generate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs... clinical trials, epidemiology... phenotypes (HPO)' — comprehensive coverage matching the 5-anchor example.	5 / 5
Completeness	Explicitly answers both 'what' ('Generate comprehensive disease research reports covering...') and 'when' ('Use for full disease overviews, comprehensive disease characterization, and orphan/rare-disease profiling'), matching the 5-anchor pattern.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('disease research reports', 'full disease overviews', 'disease characterization', 'orphan/rare-disease profiling') plus domain terms, but lacks a few common synonyms/variations and file-extension-style triggers to reach 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-database disease research) with distinct triggers ('orphan/rare-disease profiling', named databases), giving it minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 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
relative_links	Relative link issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-disease-research/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.