Name: tooluniverse-rare-disease-genomics
Rating: 68.8 (1 reviews)
Author: mims-harvard

tooluniverse-rare-disease-genomics

Rare disease genomics — disease identification (Orphanet), causative gene discovery, gene-disease validity (GenCC), variant interpretation (ClinVar), and translational research (ClinicalTrials.gov, drug repurposing for orphans). Use for rare-disease-gene curation, novel-gene-discovery analysis, and rare-disease drug-development support.

Quality

84%

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-rare-disease-genomics in mims-harvard/ToolUniverse

Quality

Content

76%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 highly actionable with exact tool/parameter signatures and complete example workflows, and is well-structured by phase. The main weakness is workflow clarity: validation is a post-hoc checklist rather than explicit validate-then-proceed checkpoints embedded in the phased flow.

Suggestions

Embed explicit validation checkpoints inside the phased workflow (e.g., after Phase 0, assert the ORPHA code is the exact disease not a subtype/umbrella before proceeding), turning the end-of-document checklist into gated steps.

Add a short validate-then-fix feedback loop for the variant-prioritization reasoning steps (e.g., if phenotype-genotype correlation fails, loop back to re-check inheritance mode and allele frequency).

Consider extracting the per-tool API/parameter catalog into a one-level-deep reference file (e.g., references/tools.md) so SKILL.md reads as an overview pointing to the detailed tool signatures.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with exact tool/parameter signatures and no padding of concepts Claude already knows, though a few heuristic-prose sections ("Resist the urge to skip to ClinVar," submitter-consensus explanations) could be tightened slightly.	4 / 5
Actionability	Nearly every tool lists its required parameters, aliases, defaults, and types, plus two complete copy-pasteable example workflow call sequences and an explicit parameter-mistake correction list — fully executable guidance for the common cases.	5 / 5
Workflow Clarity	A clear nine-phase sequence with an ordering rationale and an end completeness checklist exists, but validation is implicit (a post-hoc checklist) rather than explicit validate-then-proceed checkpoints gated within the phases.	3 / 5
Progressive Disclosure	Well-organized into clearly signaled sections (phases, evidence grading, fallbacks, examples, checklist) in a single ~280-line file with no bundle references; minor gap is that the per-tool API catalog and example workflows are inlined rather than split into a one-level-deep reference file.	4 / 5
	Total	16 / 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.

The description is concrete, well-scoped, and answers both what the skill does and when to use it, with named data sources and an explicit trigger clause. Minor gains are available by adding a few more natural user phrasings (e.g., "genetic cause of," HPO terms) to the trigger set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (disease identification, causative gene discovery, gene-disease validity, variant interpretation, translational research) each tied to named data sources (Orphanet, GenCC, ClinVar, ClinicalTrials.gov), giving comprehensive coverage of the domain's capabilities.	5 / 5
Completeness	Clearly states both "what" (the five action areas and their source databases) and an explicit "when" clause ("Use for rare-disease-gene curation, novel-gene-discovery analysis, and rare-disease drug-development support").	5 / 5
Trigger Term Quality	Strong natural keyword coverage ("rare disease," "drug repurposing for orphans," "rare-disease-gene curation," "novel-gene-discovery analysis"), but a few common user phrasings present in the body (e.g., "genetic cause of," "HPO phenotypes for") are absent from the description.	4 / 5
Distinctiveness Conflict Risk	A clear rare-disease-genomics niche anchored to distinct databases, with explicit boundary guidance against sibling skills (common disease, cancer, GWAS, pharmacogenomics) keeping conflict risk minimal.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-rare-disease-genomics/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.