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

76%

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-precision-medicine-stratification/SKILL.md

Quality

Content

65%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, tool-specific orchestration guide with concrete parameter guidance and clear phase sequencing. Its main weaknesses are missing validation checkpoints in the batch workflow and referenced bundle files that do not exist, undermining both executability and progressive disclosure.

Suggestions

Add explicit validation checkpoints between phases (e.g., "Verify gene IDs resolved before Phase 2", "Confirm disease type classified before Phase 3 routing") with error-recovery feedback loops.

Provide the referenced bundle files (TOOLS_REFERENCE.md, SCORING_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, QUICK_START.md) or inline the critical scoring matrices so the 0-100 score can actually be computed.

Include at least one concrete Python example for the "COMPUTE, DON'T DESCRIBE" section to make the analysis step copy-paste executable.

Dimension	Reasoning	Score
Conciseness	Dense, information-rich bullet/table format that mostly assumes Claude's competence; minor over-explanation remains (e.g., the opening "Stratification means splitting patients into groups..." definition and some redundant KEY PRINCIPLES framing) that could be trimmed.	4 / 5
Actionability	Concrete tool names with specific parameter gotchas (e.g., "MyGene_query_genes: param is `query` (NOT `q`)"), inline score-component ranges and risk-tier table; gaps are the absence of any executable code examples and the reliance on referenced scoring matrices that are not present in the bundle.	4 / 5
Workflow Clarity	Nine phases are clearly sequenced with numbered steps, but this batch/multi-tool workflow lacks explicit inter-phase validation checkpoints or error-recovery feedback loops (only implicit guidance like "LOOK UP DON'T GUESS"), capping it at 3 per the batch-operations rule.	3 / 5
Progressive Disclosure	A well-signaled one-level-deep reference section lists TOOLS_REFERENCE.md, SCORING_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, QUICK_START.md, but none of these bundle files actually exist, so the disclosure leads to dead ends rather than accessible detail.	3 / 5
	Total	14 / 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, third-person description that clearly states both capability and trigger conditions with concrete, domain-natural language. Minor gaps in keyword synonym coverage and some residual overlap with related tooluniverse skills 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", "personalized therapeutic strategy reports per patient subgroup" — with comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ("integrate ... data to split patients into ... groups") and when ("Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports"), with concrete trigger phrases matching the score-5 anchor.	5 / 5
Trigger Term Quality	Good natural domain keywords ("patient stratification", "precision medicine", "stratification-by-biomarker", "treatment-selection", "personalized therapeutic strategy") but a few common synonyms users might say (e.g., "responder prediction", "prognosis", "biomarker testing") are missing, placing it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (precision-medicine patient stratification) but minor overlap risk with closely related sibling skills, which the body's extensive "NOT for" list confirms is a real concern — mostly distinct rather than minimal conflict.	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: plugin/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.