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 a clear 'Use when' clause covering multiple trigger scenarios and a distinct healthcare niche. Its main weakness is some buzzword-heavy language ('AI-enhanced', 'digital twin predictions') that slightly reduces specificity, and the concrete actions could be more granular (e.g., what exactly does 'optimizing care transitions' entail). Overall it performs well for skill selection purposes.
Suggestions
Replace vague phrases like 'optimizing care transitions' and 'AI-enhanced discharge documentation' with more concrete actions (e.g., 'generates follow-up care checklists', 'flags high-risk patients for readmission').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (patient discharge) and several actions (drafting summaries, creating instructions, simulating outcomes), but some terms like 'optimizing care transitions' and 'AI-enhanced discharge documentation' are somewhat vague and buzzword-heavy rather than concrete actionable capabilities. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (generates AI-enhanced discharge documentation with digital twin predictions) and 'when' (the 'Use when' clause lists five specific trigger scenarios including drafting summaries, creating instructions, simulating outcomes, reducing readmissions, and optimizing transitions). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms a user would say: 'discharge summaries', 'discharge instructions', 'hospital readmissions', 'care transitions', 'post-discharge outcomes', and 'patient safety' are all terms healthcare professionals would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of patient discharge documentation, digital twin predictions, and readmission reduction creates a very specific niche that is unlikely to conflict with other skills. The healthcare discharge focus with digital twin simulation is highly distinctive. | 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 is excessively verbose with significant redundancy—the description appears three times, and large generic boilerplate sections (Error Handling, Input Validation, Response Template, Output Requirements) add little skill-specific value. While it contains reasonable Python examples and useful clinical checklists, the code references are inconsistent (main.py vs discharge_drafter.py) and depend on undefined objects, reducing true actionability. The workflow is abstract rather than concrete, and for a medical/safety-critical domain, the lack of explicit validation checkpoints in the technical execution path is a notable gap.
Suggestions
Remove duplicate description text from 'When to Use' and 'Key Features' sections, and eliminate generic boilerplate sections (Output Requirements, Error Handling, Input Validation, Response Template) that don't contain skill-specific guidance—this could cut the document by 40%+.
Resolve the inconsistency between scripts/main.py and scripts/discharge_drafter.py, and provide a minimal working example with defined inputs rather than referencing undefined variables like admission_info and patient_model.
Add concrete validation steps to the workflow (e.g., 'verify digital twin model loads without error', 'validate output against JCAHO schema before finalizing') especially for batch operations on patient data.
Move detailed API examples (outcome simulation, personalized instructions, risk-based planning) into a separate REFERENCE.md or EXAMPLES.md file, keeping SKILL.md as a concise overview with the Quick Start and one core example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The description is copy-pasted multiple times (in 'When to Use', 'Key Features', and the header). Contains extensive boilerplate sections (Output Requirements, Error Handling, Input Validation, Response Template) that are generic and not specific to this skill. The document is well over 200 lines with much content that doesn't earn its token cost—Claude already knows how to structure responses and handle errors. | 1 / 3 |
Actionability | Contains Python code examples that look executable but reference modules (scripts.discharge_drafter, DischargeDrafter class) whose actual existence and API are unverifiable. The CLI examples reference scripts/discharge_drafter.py while the workflow references scripts/main.py, creating confusion. The code is illustrative rather than truly copy-paste ready since it depends on undefined objects like admission_info, treatment_history, patient_model. | 2 / 3 |
Workflow Clarity | The Workflow section provides a 5-step sequence but it's entirely abstract ('Confirm the user objective', 'Validate that the request matches'). The Quality Checklist provides good checkpoints for the clinical process, but there are no validation/verification steps for the actual code execution. For batch processing of patient data (a destructive/high-stakes operation), there are no feedback loops or error recovery steps. | 2 / 3 |
Progressive Disclosure | References to 'references/' directory and 'scripts/main.py' exist but are vague—no specific files are named in references/. The document is monolithic with extensive inline content (simulation tables, all patterns, full CLI examples) that could be split into separate files. Some structure exists with headers, but the sheer volume of inline content undermines progressive disclosure. | 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
957c831
- 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.