Setup & Installation
npx skills add https://github.com/microsoft/skills --skill azure-ai-contentsafety-java
https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java
View on GitHubWhat This Skill Does
Java SDK for Azure AI Content Safety. Provides APIs to analyze text and images for harmful content across four categories: hate, sexual, violence, and self-harm. Also supports custom blocklists for domain-specific term filtering.
Azure's pre-trained models cover all four harm categories out of the box, so you skip training your own classifiers and get a severity scale you can threshold directly in your moderation logic.
When to use it
- Scanning user-submitted comments for hate speech before publishing
- Filtering uploaded images on a platform for violent or sexual content
- Building a custom blocklist of brand-specific prohibited terms
- Checking chat messages in a gaming app for self-harm language
- Running batch moderation on historical content with severity scoring