1---2name: azure-content-safety3description: Expert knowledge for Azure AI Content Safety development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. Use when using Content Safety APIs, Docker containers, blocklists, custom safety categories, or prompt shield, and other Azure AI Content Safety related development tasks. Not for Azure Security (use azure-security), Azure Defender For Cloud (use azure-defender-for-cloud), Azure Sentinel (use azure-sentinel), Azure Web Application Firewall (use azure-web-application-firewall).4---5# Azure AI Content Safety Skill
6
7This skill provides expert guidance for Azure AI Content Safety. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
8
9## How to Use This Skill
10
11> **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
12
13> **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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)
14
15This skill requires **network access** to fetch documentation content:
16- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
17- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.
18
19## Category Index
20
21| Category | Lines | Description |
22|----------|-------|-------------|
23| Troubleshooting | L36-L40 | Diagnosing and resolving Azure AI Content Safety API errors, including HTTP status codes, common failure causes, and recommended fixes or retries. |
24| Best Practices | L41-L45 | Tuning Content Safety thresholds, categories, and prompts to reduce misclassifications, plus strategies to balance safety, recall, and user experience. |
25| Decision Making | L46-L51 | Guidance on migrating apps from Content Safety preview to GA and deciding when and how to use limited-access Content Safety features and models. |
26| Architecture & Design Patterns | L52-L56 | Architectural guidance for combining cloud, hybrid, and on-device Azure AI Content Safety, including design patterns, deployment options, and integration strategies. |
27| Limits & Quotas | L57-L63 | Language coverage, building and training custom safety categories, and detecting protected/third‑party code in model outputs. |
28| Security | L64-L68 | Details on how Azure AI Content Safety encrypts data at rest, including encryption models, key management options, and compliance/security considerations. |
29| Configuration | L69-L73 | Configuring and using text blocklists in Azure AI Content Safety, including creating, managing, and applying custom blocked terms to filter harmful or unwanted content. |
30| Deployment | L74-L80 | How to install, configure, and run Azure AI Content Safety Docker containers for text, image, and prompt shield analysis in your own environment. |
31
32### Troubleshooting
33| Topic | URL |
34|-------|-----|
35| Resolve Azure AI Content Safety API error codes | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/response-codes |
36
37### Best Practices
38| Topic | URL |
39|-------|-----|
40| Reduce false positives and negatives in Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance |
41
42### Decision Making
43| Topic | URL |
44|-------|-----|
45| Migrate apps from Content Safety preview to GA | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/migrate-to-general-availability |
46| Decide when to use limited access Content Safety features | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/limited-access |
47
48### Architecture & Design Patterns
49| Topic | URL |
50|-------|-----|
51| Design hybrid and on-device Content Safety solutions | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/embedded-content-safety |
52
53### Limits & Quotas
54| Topic | URL |
55|-------|-----|
56| Check language support for Azure AI Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/language-support |
57| Create and train custom categories with Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-custom-categories |
58| Use protected material detection for code outputs | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-protected-material-code |
59
60### Security
61| Topic | URL |
62|-------|-----|
63| Understand data-at-rest encryption in Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/encrypt-data-at-rest |
64
65### Configuration
66| Topic | URL |
67|-------|-----|
68| Configure and use text blocklists in Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/use-blocklist |
69
70### Deployment
71| Topic | URL |
72|-------|-----|
73| Deploy image analysis Content Safety container with Docker | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/image-container |
74| Install and run Azure Content Safety Docker containers | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/install-run-container |
75| Run Prompt Shields Content Safety container for prompt attacks | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/prompt-shields-container |
76| Deploy text analysis Content Safety container with Docker | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/text-container |
majiayu000