digital-twin-discharge-drafter
Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissions, or optimizing care transitions. Generates AI-enhanced discharge documentation with digital twin predictions for improved patient safety.
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/digital-twin-discharge-drafter/SKILL.mdQuality
Discovery
89%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 well-structured description with explicit 'Use when' triggers and good domain-specific terminology. The main weakness is that some capabilities are described in somewhat abstract terms ('digital twin predictions', 'simulating post-discharge outcomes') rather than concrete actions. Overall, it effectively communicates when to select this skill from a large skill library.
Suggestions
Replace abstract terms like 'digital twin predictions' and 'simulating post-discharge outcomes' with more concrete actions (e.g., 'predicts readmission risk scores', 'generates follow-up care timelines')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (patient discharge) and some actions like 'drafting discharge summaries' and 'creating personalized discharge instructions', but lacks comprehensive concrete actions. Terms like 'simulating post-discharge outcomes' and 'digital twin predictions' are somewhat vague about what specifically happens. | 2 / 3 |
Completeness | Explicitly answers both what ('Generates AI-enhanced discharge documentation with digital twin predictions') and when ('Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissions, or optimizing care transitions'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'discharge summaries', 'discharge instructions', 'hospital readmissions', 'care transitions', 'patient safety'. These are terms healthcare professionals would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on patient discharge documentation and care transitions. The combination of 'discharge summaries', 'digital twin predictions', and 'readmission reduction' creates a distinct profile unlikely to conflict with general medical or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from significant verbosity and structural inconsistencies - it references both scripts/main.py and scripts/discharge_drafter.py without clarifying their relationship, repeats the description multiple times, and includes generic boilerplate that doesn't add healthcare-specific value. While the clinical content (risk stratification tables, quality checklists, common patterns) is useful, the lack of validation workflows for AI-generated medical content is concerning for a patient safety application.
Suggestions
Remove redundant sections: eliminate the duplicate description in 'When to Use', the self-referential 'Implementation Details', and generic boilerplate (Output Requirements, Error Handling, Response Template) that doesn't add domain-specific guidance.
Clarify the actual entry point: resolve the confusion between scripts/main.py and scripts/discharge_drafter.py - specify which file exists and how to use it.
Add explicit clinical validation workflow: for healthcare AI, include mandatory steps like 'Physician must review and approve all AI-generated discharge content before patient delivery' with specific validation commands.
Split detailed content into reference files: move Core Capabilities, Common Patterns, and CLI Usage into separate files (e.g., CAPABILITIES.md, PATTERNS.md) and keep SKILL.md as a concise overview with clear navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy - the 'When to Use' section repeats the description verbatim, 'Implementation Details' references a non-existent '## Workflow' section, and there's excessive boilerplate (Output Requirements, Error Handling, Response Template) that doesn't add domain-specific value. The skill explains concepts Claude already knows about discharge planning. | 1 / 3 |
Actionability | Provides concrete Python code examples and CLI commands that appear executable, but the code references modules (scripts/discharge_drafter.py, DischargeDrafter class) that may not exist given the earlier reference to scripts/main.py. The disconnect between documented entry points creates confusion about what's actually executable. | 2 / 3 |
Workflow Clarity | Contains a Quality Checklist with clear pre/post-discharge steps and a generic 5-step workflow, but lacks explicit validation checkpoints for the AI-generated content. For a healthcare skill involving patient safety, missing validation steps for clinical accuracy and no feedback loops for error recovery in the discharge generation process is a significant gap. | 2 / 3 |
Progressive Disclosure | References 'references/' directory and 'scripts/' but doesn't clearly signal what's in those files. The document is monolithic with extensive inline content (Core Capabilities, Common Patterns, CLI Usage) that could be split into separate reference files. Navigation between sections is unclear. | 2 / 3 |
Total | 7 / 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 | |
- Repository
- aipoch/medical-research-skills
- Commit
4a48721
- 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.