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.
52
58%
Does it follow best practices?
Impact
—
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 solid skill description with an explicit 'Use when' clause covering multiple trigger scenarios and good domain-specific terminology. Its main weakness is that some capability descriptions lean toward buzzwords ('AI-enhanced', 'digital twin predictions', 'optimizing care transitions') rather than concrete, specific actions. Overall it performs well on completeness and distinctiveness.
Suggestions
Replace buzzword-heavy phrases like 'AI-enhanced discharge documentation with digital twin predictions' with more concrete descriptions of what the skill actually produces (e.g., 'Generates discharge summaries with predicted readmission risk scores and recommended follow-up schedules').
| 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: drafting summaries, creating instructions, simulating outcomes, reducing readmissions, 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', 'patient safety'. These are terms healthcare professionals would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche around patient discharge documentation with digital twin predictions. The combination of healthcare discharge context and digital twin simulation makes it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%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 severe verbosity and redundancy—the description is repeated verbatim in multiple sections, and generic boilerplate (error handling, input validation, response template) inflates token cost without adding value. The code examples appear concrete but reference inconsistent entry points (main.py vs discharge_drafter.py) and undefined objects, undermining actual actionability. The overall structure is a monolithic document with no supporting bundle files despite multiple references to external paths.
Suggestions
Remove all redundant sections: consolidate 'Example Usage', 'Quick Start', and 'CLI Usage' into a single section; remove the copy-pasted description from 'When to Use' and 'Key Features'.
Eliminate generic boilerplate sections (Output Requirements, Response Template, Error Handling, Input Validation) that teach Claude things it already knows, or compress them to 2-3 bullet points maximum.
Resolve the entry point inconsistency: clarify whether the main script is scripts/main.py or scripts/discharge_drafter.py, and provide actually executable examples with defined inputs.
Split detailed Core Capabilities, Common Patterns, and Quality Checklist content into separate referenced files to improve progressive disclosure and reduce the main skill file to an actionable overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The description is copy-pasted into multiple sections ('When to Use', 'Key Features'). Sections like 'Implementation Details' restate the workflow. Boilerplate sections (Output Requirements, Response Template, Error Handling, Input Validation) add significant token cost with generic content Claude already knows. The skill explains concepts like health literacy levels and care transitions that are general medical knowledge. | 1 / 3 |
Actionability | The Python code examples in Quick Start and Core Capabilities look concrete but are not truly executable—they reference undefined objects (admission_info, treatment_history, patient_model) and import from modules (scripts.discharge_drafter) whose existence is unverified since no bundle files are provided. CLI examples reference scripts/discharge_drafter.py while other sections reference scripts/main.py, creating confusion about the actual entry point. | 2 / 3 |
Workflow Clarity | The Workflow section provides a 5-step sequence but it's generic and abstract ('Confirm the user objective', 'Use the packaged script path'). The Quality Checklist provides good pre/post-discharge checkpoints, but there are no validation feedback loops for the actual technical execution. Batch processing is mentioned in CLI usage with no validation or error recovery steps, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text at ~250+ lines with no external file references that resolve to actual content (no bundle files provided). It references 'references/' directory and 'scripts/main.py' but these don't exist. Content that could be split (Core Capabilities details, Common Patterns, CLI examples) is all inline. Multiple redundant sections cover similar ground (Example Usage, Quick Start, CLI Usage, Workflow, Implementation Details). | 1 / 3 |
Total | 6 / 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
d3c2c0f
- 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.