medical-case-report-generator

Generates a patient-friendly medical case report tweet from case images and disease name. Use when the user provides a medical case image and wants a structured report or tweet.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/medical-case-report-generator/SKILL.md

Quality

Content

46%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 workflow is clearly sequenced and well-structured with a real bundled validation script, but it is padded with generic templated boilerplate and lacks executable methods or validation feedback loops between steps. Tightening the template prose and adding concrete extraction tools would most improve it.

Suggestions

Remove the generic templated sections (When to Use, Key Features, Implementation Details, Quick Validation) that restate the description or state what Claude already knows, keeping only the concrete Medical Case Report Generator workflow.

Specify concrete methods or tools for image text extraction (e.g. a named OCR approach or prompt) instead of the abstract 'Perform image enhancement, correction, and validation'.

Add explicit validation checkpoints between workflow steps (e.g. verify extracted text is legible before patient-info extraction, confirm anonymization before disease generation) to create validate-then-proceed feedback loops.

Dimension	Reasoning	Score
Conciseness	The body carries substantial templated boilerplate ('Use this skill when the request matches its documented task boundary', 'Scope-focused workflow aligned to:', 'See `## Workflow` above for related details') that restates the description and adds generic guidance Claude already knows, fitting 'noticeably verbose; several unnecessary ... padded sections'.	2 / 5
Actionability	Field lists, output-format templates, and concrete rules (e.g. '18-25 characters', 'Start with prefix: 【Case Report】') are actionable, but steps like 'Extract printed and handwritten medical text' and 'Perform image enhancement, correction, and validation' lack specific methods or tools, leaving guidance incomplete.	3 / 5
Workflow Clarity	The six-step Input/Action/Output sequence is clearly ordered, but inter-step validation checkpoints are absent or only implicit, and privacy-sensitive medical extraction without explicit validate-then-proceed feedback loops caps clarity at 3.	3 / 5
Progressive Disclosure	Content is well-sectioned with clear headers and the referenced `scripts/validate_skill.py` is a real one-level-deep bundle file, though most material is inlined in a single file rather than split into references, leaving minor organization gaps.	4 / 5
	Total	12 / 20 Passed

Description

78%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 is well-formed, clearly stating both the task and explicit trigger conditions with a distinct medical-report niche. Its main limitation is specificity, naming one composite action rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('patient-friendly medical case report tweet') and the core action ('Generates ... from case images and disease name'), but covers only one composite action rather than multiple specific capabilities, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both 'what' (generates a patient-friendly medical case report tweet from case images and disease name) and 'when' (Use when the user provides a medical case image and wants a structured report or tweet) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('medical case image', 'structured report', 'tweet') with good coverage; only a few synonyms/variations are missing, fitting the 'good keyword coverage' anchor.	4 / 5
Distinctiveness Conflict Risk	The medical-case-report-to-tweet niche is mostly distinct with clear triggers, but there is minor overlap risk with broader medical/clinical reporting skills, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/medical-case-report-generator/SKILL.md
Commit: f5ef65b

Reviewed: ~18 hours ago

Table of Contents

Discovery Implementation Validation

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.