tooluniverse-precision-medicine-stratification

Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease/condition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis across 9 phases covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment (Low/Intermediate/High/Very High), treatment algorithm (1st/2nd/3rd line), pharmacogenomic guidance, clinical trial matches, and monitoring plan. Use when clinicians ask about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy across cancer, metabolic, cardiovascular, neurological, or rare diseases.

Quality

78%

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 ./skills/med/tooluniverse-precision-medicine-stratification/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete, executable tool calls and a clearly sequenced 9-phase workflow, but it is an oversized monolith that would benefit from splitting reference material into separate files and adding explicit validation/feedback loops between phases.

Suggestions

Split the Phase 0 tool-parameter reference, gene-ID tables, and scoring tables into reference files (e.g. TOOL_PARAMS.md, GENE_IDS.md, SCORING.md) and link to them from a leaner SKILL.md overview.

Add explicit validation checkpoints between phases (e.g. verify EFO/gene resolution succeeded before Phase 2, confirm at least one genetic layer returned data before scoring) with retry guidance on failure.

Tighten prose and consolidate duplicated guidance-category tables to reduce the 1143-line footprint and respect the context-window budget.

Dimension	Reasoning	Score
Conciseness	Most content is operational reference (exact tool parameters, response JSON paths, score-component tables) that earns its place, but at 1143 lines the sheer volume strains the token budget and several reference blocks could be tightened or moved out, matching the mostly-efficient-but-could-be-tightened anchor.	2 / 3
Actionability	Provides abundant copy-paste-ready Python with exact tool calls, required parameters, and response-structure parsing (e.g. tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName='breast cancer') with the nested response path), matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 9 phases are clearly sequenced and there is a Phase 0 parameter-verification step plus a completeness checklist, but explicit per-phase validation gates and validate->fix->retry feedback loops are largely absent, so checkpoints are present yet incomplete.	2 / 3
Progressive Disclosure	The skill is a 1143-line monolithic file with no bundle files; large reference blocks (Phase 0 tool-parameter table, gene-ID tables, scoring tables) that should live in separate files are inline, matching the structure-present-but-content-should-be-separate anchor.	2 / 3
	Total	9 / 12 Passed

Description

92%

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 strong: it specifies concrete actions, gives an explicit 'Use when...' trigger, and answers both what and when in third-person voice. Its only weakness is moderate overlap with a family of related genomic-analysis skills.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis...') and specific outputs ('Precision Medicine Risk Score (0-100) with risk tier assignment... treatment algorithm... monitoring plan'), matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states both what the skill does (multi-phase analysis, quantitative score and outputs) and when to use it via an explicit 'Use when...' trigger clause, satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	'Use when clinicians ask about patient risk stratification, treatment selection, prognosis prediction, or personalized therapeutic strategy' provides good coverage of natural terms a clinician would say, fitting the natural-keywords anchor.	3 / 3
Distinctiveness Conflict Risk	The integrated multi-phase stratification niche is fairly clear, but triggers like 'treatment selection' and 'prognosis prediction' overlap with sibling tooluniverse skills (immunotherapy-response-prediction, variant-interpretation), so it could still trigger the wrong skill.	2 / 3
	Total	11 / 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
skill_md_line_count	SKILL.md is long (1144 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/med/tooluniverse-precision-medicine-stratification/SKILL.md
Commit: df37802

Reviewed: 2 days 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.