usmle-case-generator
Generate USMLE Step 1/2 style clinical cases with patient history, physical.
44
31%
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/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 appears truncated and lacks completeness. It is missing a 'Use when...' clause, which is critical for skill selection, and the capability list is cut short (ending with 'physical.' suggesting more was intended). The trigger terms are adequate but could be expanded with common user phrasings.
Suggestions
Add a 'Use when...' clause with trigger terms like 'USMLE prep', 'board questions', 'clinical vignettes', 'practice cases', 'medical board exam'.
Complete the truncated description to list all specific actions, e.g., 'Generate USMLE Step 1/2 style clinical cases with patient history, physical exam findings, lab results, imaging, differential diagnosis, and answer explanations.'
Include common user phrasing variations such as 'board prep', 'Step 2 CK', 'practice questions', 'medical vignettes' 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 | Describes what it does (generates USMLE-style clinical cases) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also incomplete (appears truncated), warranting a score of 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', 'vignettes', '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 medical exam focus and specific exam type make it clearly distinguishable. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
22%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 sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that have nothing to do with USMLE case generation and consume significant token budget. The domain-specific content—how to construct medically accurate clinical vignettes, what makes a good USMLE question, common pitfalls in case generation—is almost entirely absent. The circular self-references ('See ## Features above') suggest auto-generated content that was not reviewed.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements) that don't contain USMLE-specific guidance—these waste tokens on content Claude already knows.
Add domain-specific workflow steps for medical case generation: e.g., how to select appropriate distractors, how to ensure clinical accuracy, what makes a Step 1 vs Step 2 case distinct in construction.
Fix circular references ('See ## Features above', 'See ## Usage above', 'See ## Workflow above') by consolidating content into a logical order and removing redundant pointers.
Add a validation checkpoint for medical accuracy review, given the skill's own warning that cases may contain inaccuracies—this is a critical missing feedback loop.
| 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 of generating USMLE cases. Multiple sections reference each other circularly ('See ## Features above', 'See ## Usage above'). The skill explains obvious concepts and includes unnecessary scaffolding that wastes tokens. | 1 / 3 |
Actionability | Provides concrete CLI commands with parameters and a parameter table, plus an example output showing case structure. However, much of the 'actionable' content is generic boilerplate (error handling, input validation, response templates) rather than domain-specific guidance on how to actually generate medically accurate USMLE cases. The core medical knowledge needed to produce quality cases is absent. | 2 / 3 |
Workflow Clarity | The workflow section is entirely generic ('Confirm the user objective', 'Validate that the request matches the documented scope') with no USMLE-specific steps. There are no validation checkpoints for medical accuracy, which is critical given the skill's own warning that cases may contain inaccuracies. The 'Example run plan' is also generic. For a skill involving medical content generation, missing clinical validation steps is a serious gap. | 1 / 3 |
Progressive Disclosure | References to external files (references/topics.json, references/case_templates.json, etc.) are present and clearly listed. However, the main file itself is a monolithic wall of text with many sections that could be split out (Security Checklist, Risk Assessment, Evaluation Criteria). Circular internal references ('See ## Features above') add confusion rather than clarity. | 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.
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
8277276
- 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.