azure-ai-contentsafety-java

Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual conten...

Install with Tessl CLI

npx tessl i github:boisenoise/skills-collections --skill azure-ai-contentsafety-java

What are skills?

Quality

89%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SKILL.md

Review

Evals

Evaluation results

100%

18%

Comment Moderation Service

Text analysis with category filtering and severity thresholds

Criteria

Without context

With context

Correct artifact ID

100%

Correct SDK version

100%

Client builder pattern

100%

Environment variable endpoint

100%

Environment variable key

100%

KeyCredential usage

100%

Category filtering

100%

Eight severity levels

100%

Blocking threshold

100%

HttpResponseException handling

100%

Result iteration

100%

Without context: $0.3282 · 3m 8s · 18 turns · 23 in / 5,416 out tokens

With context: $0.4437 · 3m 10s · 23 turns · 293 in / 5,020 out tokens

100%

10%

Custom Term Blocklist Manager

Blocklist CRUD management

Criteria

Without context

With context

BlocklistClientBuilder

100%

BlocklistClient credentials

100%

createOrUpdateTextBlocklistWithResponse

100%

201 vs 200 distinction

100%

addOrUpdateBlocklistItems method

100%

listTextBlocklists method

100%

listTextBlocklistItems method

100%

removeBlocklistItems method

100%

deleteTextBlocklist method

100%

Propagation delay documented

100%

Correct SDK version in pom

100%

Without context: $0.5942 · 5m 33s · 23 turns · 71 in / 10,676 out tokens

With context: $0.4076 · 2m 58s · 20 turns · 23 in / 5,141 out tokens

100%

12%

Multi-Layer Content Filter for Customer Support

Blocklist-integrated text analysis and batch processing

Criteria

Without context

With context

setBlocklistNames

100%

setHaltOnBlocklistHit

100%

getBlocklistsMatch null check

100%

TextBlocklistMatch fields

100%

Concurrent processing

100%

Client env var credentials

100%

KeyCredential usage

100%

Correct SDK version

100%

Harm category result output

100%

ContentSafetyClientBuilder usage

100%

Error handling present

50%

100%

Without context: $0.5071 · 5m 9s · 25 turns · 31 in / 7,806 out tokens

With context: $0.6002 · 4m 27s · 28 turns · 74 in / 7,671 out tokens

Evaluated: 4 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Comment Moderation Service Custom Term Blocklist Manager Multi-Layer Content Filter for Customer Support

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.