pyhealth

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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, highly actionable skill body with excellent progressive disclosure and concrete executable code throughout. The main weakness is conciseness — the duplicate end-to-end workflow examples and repetitive use-case reference pointers could be consolidated.

Suggestions

Consolidate the 'Quick Start Workflow' and 'Example: Complete Workflow' into a single example to remove ~90 lines of near-duplicate training-pipeline code.

Compress the six 'Common Use Cases' into a compact table mapping objective → reference files, instead of repeating the same reference pointers per use case.

Add an explicit validation/feedback loop note in the training workflow (e.g., 'if validation metric degrades, reduce capacity or adjust preprocessing and re-train') to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no concept-explanation padding, but the body is ~480 lines with notable redundancy — the Quick Start Workflow and the later 'Example: Complete Workflow' cover near-identical training pipelines, and the six Common Use Cases repeat the same reference pointers.	3 / 5
Actionability	Fully executable, copy-paste-ready Python code in both the Quick Start and Complete Workflow examples, a concrete install command, and inline code snippets in Best Practices covering splitting, stats, and monitoring.	5 / 5
Workflow Clarity	Clear numbered sequences (5-step Quick Start, 10-step Complete Workflow) with monitoring checkpoints and checklists in Best Practices, but no explicit validate→fix→retry feedback loop for error recovery.	4 / 5
Progressive Disclosure	Exemplary one-level-deep structure: the body is an overview pointing to 6 real, well-named reference files (all verified present), each signaled with 'Read when' triggers and 'Key Topics', making navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

95%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, comprehensive description that clearly states what the skill does and when to use it, with rich natural trigger terms and a distinct healthcare-AI niche. The only minor weakness is that the top-level action verbs (develop/test/deploy) are somewhat generic, though domain coverage is thorough.

Dimension	Reasoning	Score
Specificity	The description lists concrete actions ('developing, testing, and deploying machine learning models') plus comprehensive domain coverage (mortality, readmission, drug recommendation, ICD/NDC/ATC, EEG/ECG, MIMIC-III/IV, eICU, OMOP, RETAIN, SafeDrug), but the core verbs are slightly high-level compared to the fully concrete action list in the 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data') and 'when' ('This skill should be used when working with...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and specific names users would actually say: EHR, mortality, readmission, drug recommendation, ICD/NDC/ATC, EEG/ECG, MIMIC-III/IV, eICU, OMOP, RETAIN, SafeDrug, Transformer, GNN.	5 / 5
Distinctiveness Conflict Risk	Healthcare AI is a clear niche with highly distinct triggers (EHR, MIMIC, ICD, SafeDrug); minimal overlap risk with general ML skills.	5 / 5
	Total	19 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/pyhealth/SKILL.md
Commit: d5ae560

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.