tdg-personal/healthcare-cdss-patterns
Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.
83
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 a strong description with excellent specificity and domain-specific trigger terms that clearly carve out a distinct niche. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding trigger guidance would elevate this from good to excellent.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when building clinical decision support features, implementing drug interaction checks, dose calculators, clinical scoring tools, or integrating clinical alerts into EMR/EHR systems.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: drug interaction checking, dose validation, clinical scoring with named examples (NEWS2, qSOFA), alert severity classification, and EMR workflow integration. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this dimension at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'drug interaction', 'dose validation', 'clinical scoring', 'NEWS2', 'qSOFA', 'alert severity', 'EMR', 'CDSS'. These are terms a developer in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in clinical decision support with specific medical terminology (NEWS2, qSOFA, EMR workflows) that is very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill for CDSS development with excellent executable code examples, clear safety constraints, and well-defined testing patterns. Its main weaknesses are moderate verbosity from duplicated examples and a monolithic structure that could benefit from splitting detailed reference material (scoring tables, interaction databases) into separate files. The safety-critical aspects are handled exceptionally well with explicit fail-safe patterns and anti-patterns.
Suggestions
Remove the Examples section at the bottom or significantly trim it, since the inline code in each subsection already demonstrates usage with comments showing expected output.
Add references to external files for detailed content: e.g., 'See SCORING_TABLES.md for complete NEWS2/qSOFA/APACHE scoring specifications' and 'See INTERACTION_DATA.md for interaction pair data model and maintenance guide'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient for a complex domain, but includes some redundancy — the code examples in the Examples section largely repeat what's already shown in the main implementation sections. The architecture diagram and interface definitions are valuable, but the overall length (~200 lines) could be tightened by removing duplicate demonstrations. | 2 / 3 |
Actionability | Provides fully executable TypeScript code with complete interfaces, function signatures, and concrete implementations. The testing patterns are copy-paste ready, the alert severity table gives precise UI behavior specs, and the examples show exact input/output pairs. | 3 / 3 |
Workflow Clarity | The architecture flow diagram clearly shows the data path from EMR UI through CDSS engine back to UI. Validation is deeply embedded in the workflow — weight-missing blocks, bidirectional interaction checks, 100% pass criteria for tests, and explicit anti-patterns that serve as validation guardrails. The dose validation function itself is a multi-step workflow with clear sequencing and fail-fast behavior. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic document with no references to external files for detailed content like scoring tables, interaction pair databases, or extended API references. The NEWS2 scoring tables are mentioned but not provided, and there's no pointer to where they live. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents