discharge-summary-writer
Generate hospital discharge summaries from admission data, hospital course, medications, and follow-up plans. Trigger when user needs to create a discharge summary, compile inpatient medical records, or generate post-hospitalization documentation for patients.
Install with Tessl CLI
npx tessl i github:aipoch/medical-research-skills --skill discharge-summary-writer82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%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-crafted skill description that excels across all dimensions. It provides specific capabilities with clear medical domain context, includes natural trigger terms healthcare users would employ, explicitly states both what the skill does and when to use it, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate hospital discharge summaries from admission data, hospital course, medications, and follow-up plans.' This clearly describes the inputs and output with domain-specific detail. | 3 / 3 |
Completeness | Clearly answers both what (generate discharge summaries from specific data types) AND when (explicit 'Trigger when' clause with multiple scenarios: create discharge summary, compile inpatient records, generate post-hospitalization documentation). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'discharge summary', 'inpatient medical records', 'post-hospitalization documentation', 'patients', 'admission data'. These are terms healthcare professionals would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to hospital discharge documentation with distinct medical terminology. Unlikely to conflict with other skills due to the narrow healthcare/inpatient focus and specific document type. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable structure for discharge summary generation with good progressive disclosure and clear input schema. However, it suffers from excessive boilerplate sections (risk assessment, security checklist, lifecycle status) that don't aid execution, and lacks concrete workflow steps with validation checkpoints for this safety-critical medical documentation task.
Suggestions
Remove boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't provide actionable guidance for Claude
Add a clear numbered workflow: 1) Validate input data completeness, 2) Generate draft summary, 3) Verify medication dosages, 4) Review for completeness, 5) Output with physician review flag
Include a concrete example showing sample input JSON and the resulting discharge summary output
Show actual code or template logic for how sections are assembled, rather than just referencing an external script
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant boilerplate sections (Risk Assessment table, Security Checklist, Evaluation Criteria, Lifecycle Status) that add little value for Claude's execution. The core content is reasonably efficient but padded with template-like sections that don't contribute to actionability. | 2 / 3 |
Actionability | Provides a clear CLI command and JSON schema for input, but lacks executable code examples showing how the script actually processes data or generates output. The script reference assumes existence of 'scripts/main.py' without showing its implementation or example output. | 2 / 3 |
Workflow Clarity | The workflow is implicit rather than explicit - there's no clear step-by-step process for generating a discharge summary. Safety considerations mention physician review but don't integrate validation checkpoints into a clear workflow sequence. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections and references to external files (discharge_template.md, medical_terms.json, section_guidelines.md). Content is appropriately organized with one-level-deep references and clear navigation. | 3 / 3 |
Total | 9 / 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 | |
- 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.