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

81%

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

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.

A well-structured, actionable research skill with clear sequencing and end-state validation, weakened by a Progressive Update Pattern that is pseudocode rather than an executable feedback loop and by a Reference Files section that points to files not present in the bundle.

Suggestions

Create the referenced bundle files (REPORT_TEMPLATE.md, RESEARCH_PROTOCOL.md, tool_usage_details.md, TOOLS_REFERENCE.md, EXAMPLES.md) or remove the dead links so progressive disclosure is one level deep and navigable.

Replace the comment-only 'Progressive Update Pattern' with an executable validate→fix→retry loop (e.g., a script that checks for remaining placeholders and re-runs), since this is a batch operation over 10 dimensions.

Move the large inlined report template into REPORT_TEMPLATE.md and keep only a short pointer inline to reduce token load and improve conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence ('LOOK UP, DON'T GUESS', disease-mechanism reasoning) without over-explaining basics, though the report template and expected-output-scale sections could be tightened by offloading to bundle files.	4 / 5
Actionability	Provides an executable ZOOMA code example and a concrete report template, but the per-dimension tool calls are delegated to a non-existent tool_usage_details.md and the 'Progressive Update Pattern' is comment-only pseudocode, leaving minor gaps.	4 / 5
Workflow Clarity	Clear report-first sequence with a final quality checklist and evidence-grading table providing end-state validation; however the mid-process 'Progressive Update Pattern' feedback loop is comment-only pseudocode rather than an explicit validate→fix→retry checkpoint, so it is not quite a full 5.	4 / 5
Progressive Disclosure	Has a clear Reference Files section signaling five bundle files, but none of those files (REPORT_TEMPLATE.md, RESEARCH_PROTOCOL.md, tool_usage_details.md, TOOLS_REFERENCE.md, EXAMPLES.md) actually exist in the bundle, and the large inlined report template is content that should live in a separate file.	3 / 5
	Total	15 / 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 clearly states capabilities and explicit 'Use for' triggers in third-person voice. Trigger-term coverage is good but could include more conversational synonyms a user might naturally say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across distinct sub-domains — 'covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing candidates), clinical trials, epidemiology (prevalence, incidence), and phenotypes (HPO)' — comprehensive coverage matching the score-5 anchor.	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') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('full disease overviews', 'comprehensive disease characterization', 'orphan/rare-disease profiling'), but misses common conversational variants like 'what do we know about [disease]' or 'tell me about [disease]', so a few natural terms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ToolUniverse disease research reports) with distinct triggers and minimal overlap 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: plugin/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.