usmle-case-generator
Generate USMLE Step 1/2 style clinical cases with patient history, physical.
32
27%
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/usmle-case-generator/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 distinctive niche (USMLE clinical case generation) but is truncated and lacks completeness. It fails to include a 'Use when...' clause, which is critical for Claude to know when to select this skill. The specificity of actions is also limited, listing only 'patient history, physical' without elaborating on other case components.
Suggestions
Add a 'Use when...' clause with trigger terms like 'USMLE', 'board prep', 'practice question', 'clinical vignette', 'medical exam review', 'Step 1', 'Step 2 CK'.
Complete the truncated description and list more specific actions such as 'generate lab results, imaging findings, differential diagnoses, answer choices with explanations'.
Include common user phrasing variations like 'practice cases', 'board-style questions', 'medical school exam prep' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (USMLE Step 1/2 clinical cases) and some actions (generate cases with patient history, physical), but the description is truncated and doesn't list comprehensive specific actions like differential diagnosis, lab results, answer explanations, etc. | 2 / 3 |
Completeness | Partially addresses 'what' (generate clinical cases) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also incomplete/truncated, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'USMLE', 'Step 1/2', 'clinical cases', 'patient history', and 'physical', but misses common variations users might say such as 'board prep', 'practice questions', 'vignette', 'medical exam', 'board review', or 'Step 2 CK'. | 2 / 3 |
Distinctiveness Conflict Risk | The USMLE Step 1/2 clinical case generation is a very specific niche that is unlikely to conflict with other skills. The combination of medical board exam preparation and clinical vignette generation creates a distinct trigger profile. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
14%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 (security checklists, risk assessments, lifecycle status, evaluation criteria, response templates) that has nothing to do with USMLE case generation. The domain-specific content—which should be the core value—is shallow, while the generic scaffolding dominates. Self-referential links ('See ## Features above') point to sections that appear later in the document, suggesting auto-generated content with poor quality control.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements, Input Validation) and focus exclusively on USMLE case generation guidance.
Add a concrete medical validation workflow: e.g., verify pathophysiology accuracy, check that lab values are clinically consistent, ensure answer explanations cite correct mechanisms.
Fix the broken internal references ('See ## Features above') by either reordering sections logically or removing the circular references entirely.
Replace the generic 5-step workflow with USMLE-specific steps: select condition → build clinical vignette → generate distractors → validate medical accuracy → format output.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and bloated. Contains massive amounts of boilerplate (Risk Assessment tables, Security Checklists, Lifecycle Status, Evaluation Criteria, Response Templates) that are generic filler unrelated to the specific skill. Multiple sections reference non-existent earlier sections ('See ## Features above'). Topics list, case structure (15 items), and output formats sections add little value. The skill explains obvious concepts and repeats itself extensively. | 1 / 3 |
Actionability | Provides concrete CLI commands with parameters and a parameter table, plus an example output showing case structure. However, much of the guidance is generic boilerplate rather than domain-specific actionable content. The actual medical case generation logic is opaque—there's no executable code showing how cases are constructed, just CLI invocations of a script whose existence and functionality cannot be verified. | 2 / 3 |
Workflow Clarity | The workflow section is entirely generic ('Confirm the user objective, required inputs...') with no USMLE-specific steps. There are no validation checkpoints for medical accuracy, no feedback loops for verifying clinical correctness of generated cases, and the 'Example run plan' is boilerplate. For a skill marked 'High' technical difficulty requiring medical knowledge validation, the absence of any content-validation workflow is a critical gap. | 1 / 3 |
Progressive Disclosure | The document is a monolithic wall of text with 20+ sections, many of which are generic boilerplate. References to 'See ## Features above' and 'See ## Usage above' point to sections that appear AFTER the reference, creating confusing navigation. References to bundle files (references/topics.json, scripts/main.py) cannot be verified as no bundle files are provided. Content that should be in separate files (case structure, topics list, security checklist) is inlined. | 1 / 3 |
Total | 5 / 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.