CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

55%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/digital-twin-discharge-drafter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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 and good trigger term coverage for healthcare professionals. The main weakness is that some capability descriptions lean toward marketing language ('AI-enhanced', 'digital twin predictions') rather than concrete actions. The description effectively carves out a distinct niche in patient discharge documentation.

Suggestions

Replace buzzwordy phrases like 'AI-enhanced discharge documentation with digital twin predictions' with more concrete actions such as 'predicts readmission risk scores, generates medication reconciliation lists, creates follow-up care schedules'.

DimensionReasoningScore

Specificity

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 buzzwordy rather than concrete specific actions.

2 / 3

Completeness

Explicitly answers both 'what' (generates AI-enhanced discharge documentation with digital twin predictions) and 'when' (opens with 'Use when...' clause listing five specific trigger scenarios). Both components are clearly present.

3 / 3

Trigger Term Quality

Includes strong natural keywords 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.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche combining patient discharge documentation with digital twin predictions. The specific healthcare domain focus on discharge processes and readmission reduction makes it very unlikely to conflict with other skills.

3 / 3

Total

11

/

12

Passed

Implementation

20%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a bloated, template-generated document that prioritizes the appearance of comprehensiveness over actual utility. The code examples look impressive but are not executable against any real implementation, the description is copy-pasted verbatim into multiple sections, and large portions are generic boilerplate (error handling, input validation, response template) that add no domain-specific value. The medical domain content (risk stratification tables, common patterns) has some value but is buried in noise.

Suggestions

Remove all duplicate content — the skill description appears verbatim in at least 3 places. Consolidate 'When to Use' to a single concise sentence.

Either provide truly executable code tied to the actual `scripts/main.py` implementation, or remove the fake API examples and focus on documenting the real CLI interface with concrete input/output examples.

Strip out generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) that contain no domain-specific guidance — these waste tokens on instructions Claude already follows.

Move detailed content (risk stratification tables, common patterns, quality checklists) into referenced files in `references/` and keep SKILL.md as a concise overview with navigation links.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. The description is copy-pasted multiple times (in 'When to Use', 'Key Features'). Contains massive amounts of speculative code examples for APIs that likely don't exist, boilerplate sections (Output Requirements, Response Template, Error Handling, Input Validation) that are generic templates not specific to this skill, and explains concepts Claude already knows. The skill is easily 3-4x longer than it needs to be.

1 / 3

Actionability

Despite containing many code examples, none are executable — they reference modules like `scripts.discharge_drafter.DischargeDrafter` that appear to be fictional/aspirational rather than real implementations. The CLI examples reference `scripts/discharge_drafter.py` while other sections reference `scripts/main.py`, creating confusion. The code is essentially pseudocode dressed up as real Python with no way to verify it works.

1 / 3

Workflow Clarity

There is a numbered workflow (steps 1-5) and quality checklists that provide some structure. However, the workflow steps are generic and abstract ('Confirm the user objective', 'Validate that the request matches the documented scope') rather than specific to discharge drafting. The batch processing CLI command lacks validation checkpoints, which should cap this at 2. Multiple workflow-like sections compete with each other (Example Usage run plan vs Workflow section).

2 / 3

Progressive Disclosure

The skill mentions `references/` directory for supporting materials, which is good progressive disclosure. However, the main file is monolithic — it contains extensive inline content (risk stratification tables, simulation outputs, common patterns, quality checklists) that could be split into separate reference files. The 'Implementation Details' section says 'See ## Workflow above' but Workflow appears below it, showing poor organization.

2 / 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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
aipoch/medical-research-skills
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.