CtrlK
BlogDocsLog inGet started
Tessl Logo

usmle-case-generator

Generate USMLE Step 1/2 style clinical cases with patient history, physical.

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/usmle-case-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and a thorough case structure, but it is weighed down by verbose generic boilerplate, weak workflow validation tied to the actual operation, and a broken plus several orphaned references.

Suggestions

Remove or merge the generic boilerplate sections (Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements, Audit-Ready Commands) to reduce padding and respect token budget.

Fix the broken 'references/conditions/' reference (create the directory or remove the line) and add references for the existing orphaned bundle files (guidelines.md, sample_input.json, sample_output.json).

Replace the generic Workflow with concrete checkpoints specific to case generation (e.g., validate topic/step inputs against topics.json, run py_compile, verify output against case structure).

DimensionReasoningScore

Conciseness

The body is padded with large generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling, Lifecycle Status, Evaluation Criteria, Audit-Ready Commands duplicating Quick Check) that are not USMLE-specific and add little Claude does not already know.

2 / 5

Actionability

Provides concrete, copy-paste-ready commands ('python scripts/main.py --step 1 --topic cardiology --difficulty medium'), a full parameters table, a 15-point case structure, and an example output, with only minor gaps.

4 / 5

Workflow Clarity

A sequenced Workflow with validation/fallback steps exists, but it is generic process boilerplate rather than concrete checkpoints tied to the case-generation operation, leaving validation implicit.

3 / 5

Progressive Disclosure

Section structure is reasonable and references are one-level-deep in a dedicated References section, but the referenced 'references/conditions/' path does not exist, several bundle files (guidelines.md, sample_input/output.json, requirements.txt) are never referenced, and 'See ## Features above' style pointers are awkward.

3 / 5

Total

12

/

20

Passed

Description

61%Weight 40%Scale 1-5

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 clearly identifies a specific niche and uses natural trigger terms, but it is truncated, lacks an explicit 'when to use' clause, and is not fully comprehensive in its action coverage.

Suggestions

Complete the truncated phrase ('patient history, physical') and add 1-2 more concrete actions (e.g., 'with answer explanations and educational objectives').

Add an explicit 'Use when...' clause, e.g. 'Use when preparing USMLE Step 1/2 clinical vignettes or board-style practice questions.'

Include common synonyms/extensions like 'USMLE', 'Step 1', 'Step 2 CK', 'clinical vignettes', 'board-style MCQs' to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('USMLE Step 1/2 style clinical cases') and a concrete action ('Generate ... with patient history, physical') but the sentence is truncated mid-phrase and coverage is not comprehensive.

3 / 5

Completeness

Has a clear 'what' (generate USMLE cases) but no 'Use when...' trigger clause; per guidelines a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

'USMLE Step 1/2', 'clinical cases', and 'patient history' are natural terms board-prep users would say, giving good keyword coverage, though a few synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

'USMLE Step 1/2 style clinical cases' is a specific niche with distinct triggers and only minor overlap risk with general medical-education skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
aipoch/medical-research-skills
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.