CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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, information-dense workflow document: clearly sequenced phases, disease-type routing, exact tool parameters, and a quantitative scoring framework. Its two real weaknesses are missing validation/feedback checkpoints in the workflow and — most seriously — five reference files cited as living in the same directory that are absent from the bundle, so the progressive-disclosure structure is promised but not delivered.

Suggestions

Ship the five referenced files (TOOLS_REFERENCE.md, SCORING_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, QUICK_START.md) in the bundle, or remove/inline the pointers — currently every reference is a dead link.

Add explicit validation checkpoints to the workflow, e.g., after each tool call verify the expected response shape (OpenTargets nested data wrapper, PubMed plain list) and a fallback action on failure, mirroring the gnomAD 'skip gracefully' pattern.

Show one minimal executable example (a sample tool invocation or the Python analysis pattern demanded by 'COMPUTE, DON'T DESCRIBE') so the guidance moves from tool names to copy-paste-ready usage.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, high-value specifics — tool parameter gotchas ('MyGene_query_genes: param is query (NOT q)', 'DrugBank tools: ALL require 4 params'), phase-specific tool lists, and exact enrichment library names — with almost no explanation of concepts Claude already knows. It falls short of anchor 5 only through minor redundancy (e.g., the repeated 'Scoring: See SCORING_REFERENCE.md' lines and the ~30-line 'Common Use Patterns' section that partially duplicates the reference-file pointers).

4 / 5

Actionability

Concrete, executable guidance dominates: exact tool names per phase, exact parameter corrections ('variant_id (NOT rsid)', 'species=homo_sapiens'), specific libraries ('KEGG_2021_Human', 'Reactome_2022'), numeric scoring bands, and a tier table mapping scores to management. It stops short of anchor 5 because no actual invocation syntax or code snippet is shown for any tool — the 'COMPUTE, DON'T DESCRIBE' directive says to write Python but gives no example — leaving a gap between tool name and copy-paste-ready call.

4 / 5

Workflow Clarity

The 9-phase sequence is clearly ordered with explicit routing logic ('Route to the correct Phase 3 path BEFORE running Phase 2 tools'), a disease-type classification table driving Phase 3 branches, and graceful failure handling ('gnomAD: May return Service overloaded - skip gracefully'). It matches anchor 4 rather than 5 because there are no explicit validate-then-proceed checkpoints or feedback loops — e.g., no step verifying that tool responses parsed correctly or what to do when an expected field is missing (the OpenTargets/gnomAD notes hint at this but are not woven into the workflow).

4 / 5

Progressive Disclosure

The structure is well-signaled and one level deep — a dedicated 'Reference files (same directory)' section listing TOOLS_REFERENCE.md, SCORING_REFERENCE.md, REPORT_TEMPLATE.md, EXAMPLES.md, and QUICK_START.md — but none of these files exist in the bundle (no references/, scripts/, or assets/ directories; no such files anywhere in the skill directory). Per the guideline to score against the actual bundle structure, the references are dangling: navigation promised by the body is unresolvable, which drops it below anchor 4's 'most content is appropriately placed; references mostly clear'.

3 / 5

Total

15

/

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 description: third-person voice, explicit what-and-when, concrete data classes and output group types, and domain-natural trigger phrases. Its only weaknesses are a few missing common synonyms (treatment response prediction, risk stratification) and slight overlap with adjacent prediction/interpretation skills.

Suggestions

Add common user phrasings such as 'risk stratification', 'treatment response prediction', or 'which patients will respond to treatment' to the Use-for clause to round out trigger coverage.

Sharpen the boundary against adjacent skills (e.g., note it is for multi-factor stratification rather than single-variant interpretation or immunotherapy-only prediction) to reduce conflict risk.

DimensionReasoningScore

Specificity

Quotes: 'integrate genomic, clinical, and therapeutic data', 'split patients into responder/non-responder groups, risk tiers, or treatment-decision groups' — multiple concrete actions with specific output group types, comprehensively covering the skill's capability space. It exceeds anchor 4 because the action list names the input data classes and three distinct output typologies rather than stopping at 'several actions with gaps'.

5 / 5

Completeness

The 'what' is explicit ('integrate genomic, clinical, and therapeutic data to split patients into responder/non-responder groups, risk tiers, or treatment-decision groups') and the 'when' is explicit with concrete triggers ('Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports per patient subgroup'). This matches anchor 5 exactly and is above anchor 4, whose 'when' is weaker or less specific.

5 / 5

Trigger Term Quality

Quotes: 'Use for stratification-by-biomarker, treatment-selection logic, and personalized therapeutic strategy reports' plus natural keywords like 'risk tiers' and 'responder/non-responder groups'. Good domain-natural coverage, but common user phrasings like 'which patients will respond', 'treatment response prediction', or 'risk stratification' as a standalone trigger are absent, so it falls just short of the comprehensive-with-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

Quotes: 'Patient stratification for precision medicine' establishes a clear niche with distinct triggers. Minor overlap risk remains with closely related skills the body itself names (e.g., 'Immunotherapy-specific prediction -> tooluniverse-immunotherapy-response-prediction') since 'responder/non-responder groups' could plausibly trigger that skill too — fitting anchor 4 rather than anchor 5's 'minimal conflict risk'.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.