tooluniverse-model-organism-genetics

Cross-species genetic analysis using model organism databases (MGI mouse, ZFIN zebrafish, FlyBase fruit fly, WormBase worm, SGD yeast, RGD rat, GBIF taxonomy). Maps human genes to orthologs, retrieves phenotype/expression/functional data, assesses gene function conservation, and identifies the best animal model for studying a human gene or disease.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-model-organism-genetics/SKILL.md

Quality

Content

63%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 a well-sequenced, highly actionable pipeline of concrete tool calls, but it is weighed down by verbose textbook genetics primers and a monolithic structure that inlines material better placed in reference files.

Suggestions

Move the 'Bacterial and Classical Genetics Reasoning' section into a separate reference file (e.g. CLASSICAL-GENETICS.md) and link to it, since it teaches concepts Claude already knows and inflates the core skill.

Tighten or remove definitional explanations (operon mechanics, attenuation stem-loops, Hfr mapping derivations) and keep only the non-obvious decision guidance.

Add explicit inter-phase validation checkpoints (e.g. 'confirm canonical Ensembl ID before proceeding to Phase 1') to mirror the final checklist and raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The tool-call phases are lean, but lengthy textbook primers (lac/trp operon regulation, trp attenuation, Hfr conjugation, three-point crosses, cotransduction) explain genetics Claude already knows, adding avoidable tokens.	3 / 5
Actionability	Concrete tool invocations with named parameters pervade the pipeline (e.g. EnsemblCompara_get_orthologues with target_species values, MGI_get_phenotypes with limit), giving mostly copy-paste-ready guidance with placeholder gaps.	4 / 5
Workflow Clarity	Phases 0–7 are explicitly sequenced with primary/fallback tool paths and capped by a Completeness Checklist; this is read-only retrieval so the destructive-cap does not apply, though inter-phase validation checkpoints are mostly implicit rather than explicit.	4 / 5
Progressive Disclosure	Well-sectioned with clear headers, but at ~264 lines it is monolithic with separable reference material (bacterial/classical genetics primer, per-species tool details) inlined and no external reference files to offload detail.	3 / 5
	Total	14 / 20 Passed

Description

71%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 specific and well-scoped with concrete actions and named databases, but it omits any 'Use when' trigger guidance, which caps its completeness. Adding an explicit trigger clause would lift the weakest dimension.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when mapping a human gene to model-organism orthologs, choosing an animal model for a human disease, or comparing cross-species phenotypes').

Include common synonyms and file/identifier cues users might say (e.g. 'orthologs', 'homologs', 'knockout phenotype', 'best animal model') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Maps human genes to orthologs, retrieves phenotype/expression/functional data, assesses gene function conservation, and identifies the best animal model') plus named databases, giving comprehensive coverage.	5 / 5
Completeness	Has a clear, concrete 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms ('model organism', 'orthologs', 'animal model', 'human gene', 'disease') a researcher would say, but lacks an explicit 'Use when' trigger phrase and some synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (cross-species model-organism genetics) anchored by specific databases; minor overlap risk with adjacent genomics skills, which the body's 'Not for' exclusions address.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-model-organism-genetics/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.