Azure AI Content Safety Skill
This skill provides expert guidance for Azure AI Content Safety. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
How to Use This Skill
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., L35-L120), use read_file with the specified lines. For categories with file links (e.g., [security.md](security.md)), use read_file on the linked reference file
IMPORTANT for Agent: If metadata.generated_at is more than 3 months old, suggest the user pull the latest version from the repository. If mcp_microsoftdocs tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|---|
| Troubleshooting | L37-L41 | Diagnosing and resolving Azure AI Content Safety API errors, including HTTP status codes, common failure causes, and recommended fixes or retries. |
| Best Practices | L42-L46 | Tuning Content Safety thresholds, categories, and prompts to reduce misclassifications, plus strategies to balance safety, recall, and user experience. |
| Decision Making | L47-L52 | Guidance on migrating apps from Content Safety preview to GA and deciding when and how to use limited-access Content Safety features and models. |
| Architecture & Design Patterns | L53-L57 | Architectural guidance for combining cloud, hybrid, and on-device Azure AI Content Safety, including design patterns, deployment options, and integration strategies. |
| Limits & Quotas | L58-L64 | Language coverage, building and training custom safety categories, and detecting protected/third‑party code in model outputs. |
| Security | L65-L69 | Details on how Azure AI Content Safety encrypts data at rest, including encryption models, key management options, and compliance/security considerations. |
| Configuration | L70-L74 | Configuring and using text blocklists in Azure AI Content Safety, including creating, managing, and applying custom blocked terms to filter harmful or unwanted content. |
| Integrations & Coding Patterns | L75-L79 | Using the groundedness detection API to check if AI responses are supported by source content, with request/response formats, parameters, and integration patterns |
| Deployment | L80-L86 | How to install, configure, and run Azure AI Content Safety Docker containers for text, image, and prompt shield analysis in your own environment. |
Troubleshooting
Best Practices
Decision Making
Architecture & Design Patterns
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment
