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

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

62%

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

The body is a well-structured, actionable guide for rare-disease genomics with a clear phased workflow and validation checkpoints, but it is over-long for a single file, repeats some guidance, and gives no executable code despite a compute-first directive. Splitting reference material into bundle files and tightening general-genetics explanations would raise the weaker dimensions.

Suggestions

Move the per-tool API reference and example workflows into reference bundle files (e.g. references/tools.md, references/workflows.md) and keep SKILL.md as a concise overview with one-level-deep links, improving progressive_disclosure and conciseness.

Provide at least one executable Python example for the "COMPUTE, DON'T DESCRIBE" directive (e.g., a pandas/scipy snippet analyzing retrieved ClinVar or epidemiology data) so the compute guidance is actionable rather than aspirational.

Trim general-genetics explanations Claude already knows (inheritance-mode definitions, consequence hierarchy) and de-duplicate the parameter-gotcha guidance that currently appears both inline and in "Common Mistakes to Avoid."

Dimension	Reasoning	Score
Conciseness	The body is information-dense with valuable tool-specific knowledge (parameter gotchas, association types, classification hierarchies), but at ~280 lines it also explains general genetics Claude already knows (autosomal-dominant/X-linked definitions, LoF consequences) and repeats inline guidance across "Fallback Strategies" and "Common Mistakes." It is mostly efficient but could be tightened, so it sits at the mid anchor rather than the lean top anchor.	2 / 3
Actionability	Tool-orchestration guidance is concrete and copy-paste ready (exact params, aliases, defaults, e.g. GenCC_search_gene(gene_symbol="FBN1")), but the "COMPUTE, DON'T DESCRIBE" directive demands executed Python while providing no executable code, and the example workflows are call-pseudocode sequences rather than runnable scripts. This matches the "some concrete guidance but incomplete" anchor.	2 / 3
Workflow Clarity	A clearly sequenced Phase 0–9 pipeline with an explicit Completeness Checklist and Evidence Grading tiers serving as validation checkpoints, plus "LOOK UP DON'T GUESS" verification guidance and ordering rules (phenotype -> disease -> gene -> variant), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Sections are well-organized into phases, but the skill is a monolithic ~280-line inline file with no bundle files (references/scripts/assets absent), so content that could be split out (full tool API reference, example workflows, evidence-grading detail) lives inline with no one-level-deep references — matching the "some structure, content that should be separate is inline" anchor.	2 / 3
	Total	9 / 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 specific, complete, and distinctive: it enumerates concrete capabilities with named data sources, gives an explicit Use-for clause, and occupies a well-bounded niche. It uses appropriate third-person voice without over-claiming.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions tied to named tools — "disease identification (Orphanet), causative gene discovery, gene-disease validity (GenCC), variant interpretation (ClinVar), and translational research (ClinicalTrials.gov, drug repurposing for orphans)" — matching the top anchor for specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the enumerated capabilities) and when via the clause "Use for rare-disease-gene curation, novel-gene-discovery analysis, and rare-disease drug-development support," satisfying the explicit-trigger requirement for the top anchor.	3 / 3
Trigger Term Quality	Embeds natural terms a user would say ("rare disease", "gene", "variant", "Orphanet", "drug repurposing for orphans") and the frontmatter triggers field adds broad keyword/pattern coverage, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	A clear niche (rare/orphan disease genomics) with distinctive tool-bound triggers (Orphanet, GenCC, ClinVar) and a body-level "NOT for" section separating sibling skills, making wrong-skill triggering unlikely.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-rare-disease-genomics/SKILL.md
Commit: 089eb8e

Reviewed: about 7 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.