discharge-summary-writer
Generate hospital discharge summaries from admission data, hospital course.
49
37%
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/discharge-summary-writer/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear clinical niche (hospital discharge summaries) with reasonable domain-specific terminology, making it distinctive. However, it lacks a 'Use when...' clause, provides only a single action ('generate'), and misses common keyword variations that users might employ. Adding explicit trigger guidance and more specific sub-capabilities would significantly improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause with trigger terms like 'discharge summary', 'discharge note', 'DC summary', 'patient discharge', 'clinical summary', or 'post-hospitalization documentation'.
Expand the list of concrete actions, e.g., 'Generates hospital discharge summaries including diagnosis lists, medication reconciliation, follow-up instructions, and procedure summaries from admission data and hospital course notes.'
Include common keyword variations users might say, such as 'discharge note', 'DC summary', 'patient summary', or 'clinical documentation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (hospital discharge summaries) and a couple of inputs (admission data, hospital course), but doesn't list multiple concrete actions beyond 'generate'. It could mention specific sub-tasks like medication reconciliation, follow-up instructions, diagnosis coding, etc. | 2 / 3 |
Completeness | It describes what the skill does (generate discharge summaries) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also thin, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'discharge summaries', 'admission data', and 'hospital course', which are natural clinical terms. However, it misses common variations like 'discharge note', 'patient summary', 'clinical summary', 'DC summary', or 'post-hospitalization report'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific clinical niche—hospital discharge summaries—which is unlikely to conflict with other skills. The domain-specific terminology (discharge summaries, admission data, hospital course) creates a clear and distinct trigger profile. | 3 / 3 |
Total | 8 / 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 heavily padded with generic boilerplate content that adds little value for discharge summary generation specifically. While the input JSON schema and parameter table provide useful concrete guidance, the majority of the document consists of template filler (lifecycle status, security checklists, generic evaluation criteria) that wastes tokens. The core medical domain knowledge—how to actually structure a discharge summary, what clinical logic to apply, what constitutes a good vs. bad summary—is largely absent.
Suggestions
Remove all generic boilerplate sections (Lifecycle Status, Risk Assessment, Security Checklist, Evaluation Criteria) and focus on domain-specific discharge summary guidance—what makes a clinically accurate summary, common pitfalls, and section-by-section writing rules.
Add a concrete example showing a sample input (even abbreviated) and the expected discharge summary output, so Claude knows exactly what the target artifact looks like.
Integrate validation checkpoints directly into the workflow: e.g., 'Verify all discharge medications have dosage+frequency+route before generating the medications section' and 'Cross-check discharge diagnoses against admission diagnoses and hospital course.'
Fix broken cross-references ('See ## Prerequisites above' when it appears below) and consolidate the duplicated workflow/example usage sections into a single clear sequence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Contains numerous sections that add no value (Lifecycle Status, Risk Assessment, Security Checklist, Evaluation Criteria with generic test cases). Multiple cross-references to sections that don't exist ('See ## Prerequisites above'). Generic boilerplate like 'Execution model: validate the request, choose the packaged workflow' explains nothing specific. The Audit-Ready Commands section lists `--help` three times. Much of the content is template filler that Claude already knows how to handle. | 1 / 3 |
Actionability | The input JSON schema is concrete and well-defined, and the CLI parameters table is useful. However, the actual script `scripts/main.py` is referenced but never shown or explained in terms of what it does internally. The workflow steps are generic ('Confirm the user objective') rather than specific to discharge summary generation. No example of actual output is provided, and no executable code for the core logic is shown. | 2 / 3 |
Workflow Clarity | There is a numbered workflow and an example run plan, but they are generic process steps not specific to discharge summary generation. The safety considerations mention physician review, but there's no explicit validation checkpoint integrated into the workflow (e.g., 'validate medication dosages against input before finalizing'). For a HIGH risk medical documentation task, the lack of concrete validation steps within the workflow is a significant gap. | 2 / 3 |
Progressive Disclosure | References to external files (references/discharge_template.md, references/medical_terms.json, references/section_guidelines.md) are present and clearly listed. However, the SKILL.md itself is monolithic with excessive inline content that should be in separate files (the full JSON schema, the security checklist, the risk assessment table). Multiple sections reference other sections with broken cross-references ('See ## Prerequisites above' when Prerequisites is below). | 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
e1f6461
- 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.