Setup & Installation
npx skills add https://github.com/microsoft/skills --skill azure-ai-contentsafety-py
https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-python/skills/azure-ai-contentsafety-py
View on GitHubWhat This Skill Does
Azure AI Content Safety SDK for Python connects to Microsoft's content moderation API to analyze text and images for harmful content. It classifies results across four harm categories (hate, sexual, violence, self-harm) with severity scores. Supports custom blocklists for domain-specific filtering.
Building this manually would require training and maintaining your own classifiers across four harm categories with calibrated severity levels, whereas this SDK offloads that to a managed API with a single function call per request.
When to use it
- Scanning user comments before they post to a forum
- Checking AI-generated responses for harmful content before displaying them
- Filtering uploaded images on a file-sharing platform
- Blocking domain-specific slurs or brand terms using custom blocklists
- Pre-screening support chat messages for self-harm language to trigger escalation