discharge-summary-writer
Generate hospital discharge summaries from admission data, hospital course.
36
33%
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/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 and specific clinical niche (hospital discharge summaries), which gives it strong distinctiveness. However, it lacks an explicit 'Use when...' clause, limiting its completeness, and could benefit from more concrete actions and natural trigger terms that users might employ when requesting this type of document.
Suggestions
Add a 'Use when...' clause with trigger terms like 'discharge note', 'DC summary', 'patient discharge', 'clinical summary', or 'post-hospitalization documentation'.
List more specific actions such as 'compiles diagnosis lists, medication reconciliation, follow-up instructions, and procedure summaries into structured discharge documents'.
Include common synonyms and abbreviations users might use, such as 'DC summary', 'discharge note', 'patient summary', or 'clinical discharge report'.
| 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 sections like medication reconciliation, follow-up instructions, diagnosis coding, etc. | 2 / 3 |
Completeness | Describes what the skill does (generate discharge summaries) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and since the 'when' is entirely missing, it scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'discharge summaries', 'admission data', and 'hospital course', but misses common variations users might say such as 'discharge note', 'patient summary', 'clinical summary', 'DC summary', or 'post-hospitalization report'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific clinical documentation niche—hospital discharge summaries—which is unlikely to conflict with other skills. The medical domain terminology makes it clearly distinguishable. | 3 / 3 |
Total | 8 / 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 is heavily padded with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that provide no actionable guidance for generating discharge summaries. The core clinical writing task is poorly addressed—there's no example of a completed discharge summary, no concrete writing guidance, and the workflow steps are generic rather than domain-specific. The document would benefit enormously from being cut to roughly one-third its current size while adding actual clinical content examples.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Input Validation boilerplate, Response Template) that don't contribute to the core task of generating discharge summaries—these waste token budget.
Add a concrete example showing sample patient input data mapped to a complete discharge summary output, so Claude knows exactly what good output looks like.
Replace the generic workflow steps ('Confirm the user objective', 'Validate that the request matches') with discharge-summary-specific steps that include clinical validation checkpoints (e.g., verify medication dosages match hospital course, confirm diagnosis consistency).
Eliminate redundant and self-referential content: remove duplicate --help commands in Audit-Ready Commands, remove 'See ## X above' cross-references that point to sections in the same document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Contains numerous self-referential sections ('See ## Prerequisites above', 'See ## Usage above'), redundant audit commands (--help listed 3 times), boilerplate sections (Lifecycle Status, Risk Assessment, Security Checklist, Evaluation Criteria) that add no actionable value for Claude. Many sections explain obvious concepts or repeat the same information in different forms. | 1 / 3 |
Actionability | The input JSON schema is concrete and well-defined, and the CLI parameters table is useful. However, the actual script commands are not executable without the bundle files (no bundle provided), the workflow steps are generic/abstract ('Confirm the user objective', 'Validate that the request matches'), and there's no example of actual input data mapped to expected output. The core task—how to actually compose a discharge summary—lacks concrete clinical writing guidance. | 2 / 3 |
Workflow Clarity | There is a numbered workflow, but it is generic and not specific to discharge summary generation. Steps like 'Confirm the user objective' and 'Validate that the request matches the documented scope' are boilerplate. The validation step is just py_compile (syntax check), not clinical content validation. Missing explicit checkpoints for verifying medical accuracy of generated content, despite the HIGH risk designation and safety warnings. | 2 / 3 |
Progressive Disclosure | The document is a monolithic wall of text with 20+ sections, many of which are boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria). References to bundle files (references/discharge_template.md, references/medical_terms.json, scripts/main.py) exist but no bundle is provided, making them unverifiable. Content that should be in separate files (the full JSON schema, the security checklist, the risk assessment table) is inlined, bloating the skill file significantly. | 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
73f6514
- 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.