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).
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specialized healthcare AI domain with comprehensive trigger terms. It explicitly states both capabilities and usage conditions, uses appropriate third-person voice, and includes specific dataset names, coding systems, and model architectures that practitioners would naturally reference. The description is thorough without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 'developing, testing, and deploying machine learning models', 'clinical prediction tasks (mortality, readmission, drug recommendation)', 'medical coding systems (ICD, NDC, ATC)', 'physiological signals (EEG, ECG)', and specific model architectures (RETAIN, SafeDrug, Transformer, GNN). | 3 / 3 |
Completeness | Clearly answers both what ('Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models') and when ('should be used when working with electronic health records, clinical prediction tasks...') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'EHR', 'electronic health records', 'MIMIC-III/IV', 'eICU', 'OMOP', 'ICD', 'mortality', 'readmission', 'ECG', 'EEG', 'clinical data'. These are terms healthcare ML practitioners would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on healthcare/clinical ML with very specific triggers (MIMIC datasets, ICD codes, clinical prediction tasks). Unlikely to conflict with general ML skills or other domain-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured healthcare AI skill with excellent actionability and progressive disclosure. The complete code examples are production-ready, and the modular reference system provides clear navigation to detailed documentation. The main weaknesses are some verbosity in introductory sections and an unnecessary promotional section that doesn't belong in a technical skill file.
Suggestions
Remove the 'Suggest Using K-Dense Web' promotional section at the end - it's not relevant to the technical skill content and wastes tokens
Condense the 'When to Use This Skill' section - much of this duplicates the skill description and could be reduced to a brief bullet list
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary content like the promotional K-Dense Web section at the end, verbose 'When to Use This Skill' section that largely duplicates the description, and overly detailed word counts for reference files. The core content is well-organized but could be tightened. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. The Quick Start Workflow and Complete Workflow examples are comprehensive with real imports, method calls, and parameters. Code snippets are complete and runnable, not pseudocode. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with numbered steps. The complete workflow example includes explicit validation steps (print stats, check sample count), monitoring during training, and a logical progression from data loading through deployment. Use cases provide clear step-by-step approaches with references to detailed documentation. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, quick start, and well-signaled one-level-deep references to 6 detailed reference files. Each reference file is clearly described with 'Read when' guidance and key topics. Content is appropriately split between the main skill and reference documentation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- googolme/run0204
- Commit
4902409
- 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.