azure-ai-contentsafety-java

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

Quality

60%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-contentsafety-java/SKILL.md

The canonical home for this skill is azure-ai-contentsafety-java in sickn33/agentic-awesome-skills

Quality

Content

72%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 body is highly actionable with comprehensive, executable Java examples and useful SDK-specific reference, but it is a monolithic single-file reference lacking progressive disclosure to deeper files and provides no validation checkpoints around destructive blocklist operations.

Suggestions

Move the bulk API reference (e.g. full blocklist management, image analysis variants) into a separate reference file and link to it from SKILL.md to apply progressive disclosure.

Add explicit validation/verification steps around destructive blocklist operations (e.g. list-then-confirm before delete, verify creation status before adding items).

Trim the redundant 'Trigger Phrases' section and the boilerplate 'When to Use' line, folding trigger guidance into the frontmatter description instead.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight, executable code with concise section headers and SDK-specific reference detail (severity scales, harm categories), but includes minor trimmable redundancy such as the 'Trigger Phrases' list, the boilerplate 'When to Use' line, and repeated import blocks in every snippet.	4 / 5
Actionability	It provides concrete, copy-paste-ready Java using real classes and methods (ContentSafetyClient.analyzeText, AnalyzeTextOptions, BlocklistClient CRUD) across the common cases (text/image analysis, blocklist management, error handling), matching the 'fully executable, covers common cases' anchor.	5 / 5
Workflow Clarity	This is an API-pattern catalog organized by operation rather than a sequenced workflow, and the destructive blocklist operations (create/update/delete) are shown without any validation or verification checkpoint; per the rubric's destructive-operations cap this cannot exceed 3.	3 / 5
Progressive Disclosure	The content is well-sectioned with clear headers aiding navigation, but it is a monolithic single-file API reference with no bundle files and no one-level-deep references to split out bulk material, fitting the 'some structure but could be better organized; content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

48%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 the domain and tooling but uses a generic action verb and omits any explicit 'when to use' trigger guidance. It is reasonably distinct yet incomplete on the trigger/completeness axis.

Suggestions

Replace the generic 'Build content moderation applications' with concrete actions, e.g. 'Analyze text and images for hate, sexual, violence, and self-harm severity; manage custom blocklists'.

Add an explicit trigger clause such as 'Use when the user asks to moderate content with Azure AI Content Safety in Java, detect harmful/hate content, or manage blocklists'.

Include natural synonyms users say ('hate speech detection', 'toxic content filter') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('content moderation') and the specific SDK/language, but the only action ('Build content moderation applications') is generic and not a concrete operation, matching the 'names the domain but actions are minimal or generic' anchor rather than the multi-action anchor at 3.	2 / 5
Completeness	It clearly states what the skill does but provides no 'Use when…' clause or equivalent trigger guidance; per the rubric guidelines a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant natural terms ('content moderation', 'Azure', 'Java') but omits common variations and synonyms a user might say (e.g. 'hate speech', 'toxic content', 'harmful content filter'), fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Azure AI Content Safety SDK for Java is a specific niche with low conflict risk, but the absence of an explicit when/trigger clause leaves minor overlap risk with related Azure or moderation skills, placing it at the 'mostly distinct' anchor rather than 5.	4 / 5
	Total	12 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/azure-ai-contentsafety-java/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.