azure-ai-vision-imageanalysis-java

Build image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-vision-imageanalysis-java/SKILL.md

Quality

Content

57%Scale 1-3

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

This skill provides highly actionable, executable Java code examples covering all Azure AI Vision features, which is its primary strength. However, it suffers from being a long monolithic document with repetitive patterns that could benefit from better organization and progressive disclosure. The workflow guidance is adequate for individual API calls but lacks validation steps for deployment concerns like regional availability checks.

Suggestions

Extract the 8 individual feature examples into a separate EXAMPLES.md file, keeping only 1-2 representative examples (e.g., Caption + OCR) in the main SKILL.md with references to the full examples.

Add a validation workflow for common failure points: check regional availability for Caption/Dense Captions features before deployment, validate image size/format before API calls, and include a retry pattern for transient errors.

Remove the boilerplate 'Trigger Phrases', 'When to Use', and 'Limitations' sections which add no actionable value and waste tokens.

Condense repetitive code patterns by showing one complete example then noting the pattern variations (e.g., 'Replace VisualFeatures.CAPTION with VisualFeatures.TAGS and access result.getTags()') rather than full code blocks for each.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with executable code examples, but includes some unnecessary sections like 'Trigger Phrases', 'When to Use', and 'Limitations' boilerplate that add no value. The feature table descriptions are brief but the overall document is long (~200 lines) with repetitive patterns across 8+ similar code examples that could be condensed.	2 / 3
Actionability	Every feature is demonstrated with fully executable, copy-paste-ready Java code including proper imports, client creation, and result processing. The Maven dependency, environment variables, and image requirements provide complete setup guidance.	3 / 3
Workflow Clarity	The skill presents individual feature examples clearly but lacks a cohesive workflow sequence. There's basic error handling shown but no validation checkpoints or feedback loops for common failure scenarios like invalid endpoints, unsupported regions for Caption features, or image size/format validation before API calls.	2 / 3
Progressive Disclosure	The content is a monolithic wall of code examples with no references to external files or separation of concerns. The 8 nearly identical analyze patterns could be condensed into a summary with a reference to a detailed examples file, and the API reference table could be separated out.	1 / 3
	Total	8 / 12 Passed

Description

100%Scale 1-3

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 clearly specifies the technology stack (Azure AI Vision SDK for Java), lists concrete capabilities (captioning, OCR, object detection, tagging, smart cropping), and includes an explicit 'Use when' clause with natural trigger terms. It uses proper third-person voice and is concise without being vague.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'image captioning, OCR text extraction, object detection, tagging, smart cropping' along with the specific technology stack 'Azure AI Vision SDK for Java'.	3 / 3
Completeness	Clearly answers both what ('Build image analysis applications with Azure AI Vision SDK for Java') and when ('Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping') with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'image analysis', 'image captioning', 'OCR', 'text extraction', 'object detection', 'tagging', 'smart cropping', 'Azure AI Vision', 'Java'. These cover common variations of how users would describe these tasks.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive due to the specific combination of Azure AI Vision SDK, Java, and the enumerated computer vision tasks. Unlikely to conflict with generic image processing or other cloud provider vision skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

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 — 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: popey/claude-code-skills
Path: skills/azure-ai-vision-imageanalysis-java/SKILL.md
Commit: a5a6601

Reviewed: 5 days 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.