Name: tooluniverse-precision-medicine-stratification
Rating: 68 (1 reviews)
Author: mims-harvard

tooluniverse-precision-medicine-stratification

Patient stratification for precision medicine — integrate genomic, clinical, and therapeutic data to split patients into responder/non-responder groups, risk tiers, or treatment-decision groups. Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports per patient subgroup.

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

The canonical home for this skill is tooluniverse-precision-medicine-stratification in mims-harvard/ToolUniverse

Quality

Content

75%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-organized, domain-rich stratification workflow with concrete tool guidance and clear phase sequencing. It falls short of top marks mainly due to the absence of executable code examples and missing referenced bundle files that the navigation points to.

Suggestions

Add one or two copy-paste executable examples (e.g., a Python snippet showing a representative tool call with real parameters and expected output) to lift actionability from concrete guidance to fully executable.

Include the referenced files (TOOLS_REFERENCE.md, SCORING_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, QUICK_START.md) in the bundle, or inline the most critical content so navigation is not broken.

Add an explicit validation/feedback loop for Phase 9 (e.g., a report-completeness checklist with a re-check-on-failure step) to strengthen workflow clarity for the integrated scoring output.

Dimension	Reasoning	Score
Conciseness	Phase lists are terse with tool names and no generic concept padding, but the intro line restates the description and the 7-item "KEY PRINCIPLES" list plus "Reasoning Before Searching" introduce mild redundancy that could be trimmed.	4 / 5
Actionability	Concrete tool names with specific parameter gotchas (e.g., "MyGene_query_genes: param is `query` (NOT `q`)") and exact enrichment library names are given, but there are no copy-paste executable code blocks demonstrating a full tool call with expected output.	4 / 5
Workflow Clarity	A clear 9-phase sequence with explicit Phase 3 disease routing and a "LOOK UP DON'T GUESS" guardrail is present, but there is no explicit validate→fix→retry feedback loop for the integrated scoring/report output, and the completeness checklist is deferred to a referenced file.	4 / 5
Progressive Disclosure	Well-structured with clear headers and a dedicated reference block signaling five one-level-deep files, but the referenced files (TOOLS_REFERENCE.md, SCORING_REFERENCE.md, etc.) are absent from the bundle and some reference-destined content (param gotchas) is inlined.	4 / 5
	Total	16 / 20 Passed

Description

88%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 both the capability and the trigger conditions for patient stratification in precision medicine. Minor overlap risk with adjacent tooluniverse skills and a few missing natural trigger synonyms keep it just short of perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "integrate genomic, clinical, and therapeutic data", "split patients into responder/non-responder groups, risk tiers, or treatment-decision groups", and "personalized therapeutic strategy reports" — giving comprehensive coverage of the stratification capability.	5 / 5
Completeness	Explicitly answers both what (integrate data, split into groups/tiers, generate reports) and when ("Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "stratification-by-biomarker", "treatment-selection logic", and "personalized therapeutic strategy" are present, but a few common lay variations (e.g., "which patients respond to treatment") and synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The precision-medicine stratification niche is mostly distinct, but "treatment-selection logic" and "personalized therapeutic strategy" overlap with closely related sibling skills (e.g., immunotherapy-response-prediction, drug-target-validation).	4 / 5
	Total	18 / 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: plugins/tooluniverse/skills/tooluniverse-precision-medicine-stratification/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.