azure-ai-contentsafety-java

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

Quality

68%

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-claude/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

76%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 thorough executable Java examples and clean organization, but it functions as an API catalog rather than a sequenced workflow and lacks validation/feedback guidance for persistent blocklist operations. Trim the filler sections and add verification steps for batch operations.

Suggestions

Add validation/verification steps for batch and destructive blocklist operations (e.g. confirm item exists before removing, verify create returned 201 before adding items) to lift workflow clarity above the batch cap.

Remove or replace the contentless "When to Use" line ("This skill is applicable to execute the workflow...") and the redundant "Trigger Phrases" list, which duplicate the description's job.

Consider moving the full blocklist CRUD and image-URL reference into a separate REFERENCE.md to tighten SKILL.md into a true overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code examples under short headers with little concept padding, assuming Claude's competence. It is not 5 because the trigger-phrase list and the filler "When to Use" line ("This skill is applicable to execute the workflow...") add tokens that earn little.	4 / 5
Actionability	It provides complete, copy-paste-ready Java covering client creation, text/image analysis, blocklist CRUD, and error handling across the common cases. This matches anchor 5 (fully executable, specific examples cover common cases).	5 / 5
Workflow Clarity	It catalogs API patterns rather than sequencing a workflow, and blocklist create/add/remove/delete operations are persistent batch operations with no validation checkpoints or feedback loops. The destructive/batch guideline caps this at 3 even though individual patterns are unambiguous.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections (Installation, Client Creation, Core Patterns, Blocklist Management) in a single file with no external bundle. It is not 5 because at ~280 lines the full blocklist CRUD and image API surface could plausibly live in separate reference files, leaving minor organization gaps.	4 / 5
	Total	16 / 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 is specific to a named SDK and language with solid natural trigger terms, but it lacks any explicit "Use when..." trigger guidance and only gestures at a single generic action. Adding concrete capabilities and a when-to-use clause would lift completeness and specificity.

Suggestions

Add a "Use when..." clause naming concrete trigger phrases (e.g. analyzing text/image safety, managing blocklists, detecting hate speech in Java).

Replace the single generic action "Build content moderation applications" with 2-3 specific actions like "analyze text and images for harmful content, manage custom blocklists, apply severity thresholds".

Include common synonyms users say ("hate speech detection", "harmful content filter") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Build content moderation applications using the Azure AI Content Safety SDK for Java" names the domain (content moderation) and one concrete action (build applications), but does not enumerate specific capabilities like text/image analysis or blocklist management. It matches anchor 3 (domain + 1-2 concrete actions) and not 4 because only a single generic action is listed.	3 / 5
Completeness	It gives a clear "what" (build content moderation apps with this SDK) but has no "Use when..." or equivalent trigger guidance, which per the guidelines caps completeness at 3. Not 4 because the "when" is entirely missing rather than merely weak.	3 / 5
Trigger Term Quality	It surfaces natural terms a user would say — "content moderation", "content safety", "Azure", "Java" — giving good keyword coverage, though synonyms and file extensions are absent. It sits at anchor 4 rather than 5 because a few natural phrasings (e.g. "hate speech", "harmful content filter") are missing.	4 / 5
Distinctiveness Conflict Risk	Tying the skill to a named product plus language (Azure AI Content Safety SDK for Java) gives a clear niche with minimal overlap risk. It falls just below 5 because the generic "build content moderation applications" phrasing leaves slight breadth toward adjacent moderation skills.	4 / 5
	Total	14 / 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-claude/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.