azure-ai-contentsafety-java

Build content moderation applications using the Azure AI Content Safety SDK for Java.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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

The skill is highly actionable and concise, delivering executable Java across all core operations, but it lacks validation/feedback loops for its destructive blocklist operations and keeps a large inline API reference rather than splitting it into one-level-deep reference files.

Suggestions

Add validation/checkpoint guidance for destructive blocklist operations (e.g. list-before-delete, confirm status codes, verify removal) to raise workflow clarity.

Move the extensive blocklist-management and image-analysis sections into separate reference files (e.g. BLOCKLIST.md, IMAGE_ANALYSIS.md) with a concise overview pointing to them.

Replace the generic 'When to Use'/'Limitations' boilerplate with skill-specific guidance or remove it to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean, section-driven, and assumes Claude's competence — it avoids explaining what content moderation or SDKs are, and every code block earns its place; only minor generic filler (the placeholder 'When to Use'/'Limitations' sections) keeps it from being flawless.	3 / 3
Actionability	It provides complete, executable Java with real imports and API calls for client creation, text/image analysis, full blocklist CRUD, and error handling — copy-paste ready and free of pseudocode.	3 / 3
Workflow Clarity	Operations are individually clear and section-labeled, but the skill includes destructive/block operations (delete blocklist, remove items) with no validation checkpoints or feedback loops, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	It is a single file with no bundle references and ~200 lines of inline API reference (blocklist CRUD, image analysis) that could be split into separate reference files, matching the score-2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 specific and distinctive but incomplete: it states what the skill does without any explicit when-to-use trigger guidance, capping completeness and trigger-term quality at the mid level.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when moderating text or images, detecting hate/violence/self-harm content, or managing blocklists in Java with Azure AI Content Safety.'

Expand the action list beyond 'Build content moderation applications' to surface the analyze-text, analyze-image, and blocklist-management capabilities.

Include common user phrasings (e.g. 'content safety Java', 'image moderation', 'hate speech detection') directly in the description for stronger trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("content moderation") and a single action ("Build content moderation applications") tied to a specific SDK, but it is not comprehensive — it omits the analyze text/image and blocklist capabilities covered in the body.	2 / 3
Completeness	It clearly states the "what" but provides no "Use when..." clause or equivalent trigger guidance; per the rubric, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes some natural keywords ("content moderation", "content safety", "Java") but lacks common variations or explicit trigger guidance in the description itself, so coverage is partial rather than strong.	2 / 3
Distinctiveness Conflict Risk	Naming the specific Azure AI Content Safety SDK for Java carves out a clear, distinctive niche that is unlikely to trigger for unrelated skills, satisfying the score-3 anchor.	3 / 3
	Total	9 / 12 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: boisenoise/skills-collections
Commit: f36337d

Reviewed: 2 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.