$ loading_
Configure Azure API Management as an AI gateway for models and agents.
This appears to be a documentation-style, prompt-only skill for configuring Azure APIM as an AI Gateway, with no declared keys, remote endpoints, or local execution capability. Given its open-source Microsoft GitHub origin and moderate community adoption, overall risk is low; the main caution is that the documented downstream Azure subscription keys and configuration steps involve sensitive operational actions.
The metadata states that the skill itself requires no keys or environment variables. The README only shows how to retrieve an APIM subscription key and configure managed identity, indicating that downstream Azure resources involve sensitive credentials, but the skill itself does not declare collecting, storing, or transmitting them.
No remote endpoint is declared, and the system flags it as prompt-only. References to Azure APIM, Azure OpenAI, and curl-based testing are examples of follow-on user operations rather than built-in outbound data transfer by the skill itself.
Based on the provided material, the skill mainly offers configuration guidance and command examples, with no factual indication that it can launch local processes, run scripts, or invoke system capabilities on its own. The az/curl commands in the README are documentation examples, not evidence of automatic execution by the skill.
There is no indication that it can read or write local files, databases, or other user data resources. Its content focuses on Azure gateway configuration flows and policy guidance, with no sign of data access beyond the described scope.
The source is an open-source Microsoft GitHub repository, which is auditable, and it has some community adoption at 222 stars—both are positive indicators that lower risk. The undeclared license and unknown maintenance status add minor uncertainty, but not enough to raise it to high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "azure-aigateway" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/plugin/skills/azure-aigateway/SKILL.md 2. Save it as ~/.claude/skills/azure-aigateway/SKILL.md 3. Reload skills and tell me it's ready
Guide me to configure Azure API Management as an AI Gateway for Azure OpenAI. Include semantic caching, token limits, content safety, load balancing, and cost control policies, with implementation steps.
A step-by-step setup plan with key policies, gateway configuration details, and implementation guidance.
I have an existing API OpenAPI spec. Explain how to import it into Azure AI Gateway and convert it into an MCP tool for agents, including rate limiting and security governance.
An import and conversion workflow covering MCP enablement steps, policy examples, and security control recommendations.
Help me design a test plan for Azure AI Gateway to verify jailbreak detection, token metrics, backend switching, model governance, and content safety, and explain which metrics to monitor.
A test checklist and validation approach with key monitoring metrics and success criteria.
Configure Azure API Management (APIM) as an AI Gateway for governing AI models, MCP tools, and agents.
To deploy APIM, use the azure-prepare skill. See APIM deployment guide.
| Category | Triggers |
|---|---|
| Model Governance | "semantic caching", "token limits", "load balance AI", "track token usage" |
| Tool Governance | "rate limit MCP", "protect my tools", "configure my tool", "convert API to MCP" |
| Agent Governance | "content safety", "jailbreak detection", "filter harmful content" |
| Configuration | "add Azure OpenAI backend", "configure my model", "add AI Foundry model" |
| Testing | "test AI gateway", "call OpenAI through gateway" |
| Policy | Purpose | Details |
|---|---|---|
azure-openai-token-limit | Cost control | Model Policies |
azure-openai-semantic-cache-lookup/store | 60-80% cost savings | Model Policies |
azure-openai-emit-token-metric | Observability | Model Policies |
llm-content-safety | Safety & compliance | Agent Policies |
rate-limit-by-key | MCP/tool protection | Tool Policies |
# Get gateway URL
az apim show --name <apim-name> --resource-group <rg> --query "gatewayUrl" -o tsv
# List backends (AI models)
az apim backend list --service-name <apim-name> --resource-group <rg> \
--query "[].{id:name, url:url}" -o table
# Get subscription key
az apim subscription keys list \
--service-name <apim-name> --resource-group <rg> --subscription-id <sub-id>
GATEWAY_URL=$(az apim show --name <apim-name> --resource-group <rg> --query "gatewayUrl" -o tsv)
curl -X POST "${GATEWAY_URL}/openai/deployments/<deployment>/chat/completions?api-version=2024-02-01" \
-H "Content-Type: application/json" \
-H "Ocp-Apim-Subscription-Key: <key>" \
-d '{"messages": [{"role": "user", "content": "Hello"}], "max_tokens": 100}'
See references/patterns.md for full steps.
# Discover AI resources
az cognitiveservices account list --query "[?kind=='OpenAI']" -o table
# Create backend
az apim backend create --service-name <apim> --resource-group <rg> \
--backend-id openai-backend --protocol http --url "https://<aoai>.openai.azure.com/openai"
# Grant access (managed identity)
az role assignment create --assignee <apim-principal-id> \
--role "Cognitive Services User" --scope <aoai-resource-id>
Recommended policy order in <inbound>:
See references/policies.md for complete example.
| Issue | Solution |
|---|---|
| Token limit 429 | Increase tokens-per-minute or add load balancing |
| No cache hits | Lower score-threshold to 0.7 |
| Content false positives | Increase category thresholds (5-6) |
| Backend auth 401 | Grant APIM "Cognitive Services User" role |
See references/troubleshooting.md for details.
…
Analyze and compress Markdown to reduce tokens and improve AI efficiency.
Write, review, and standardize Agent Skills to match agentskills.io requirements.
Discover Azure OpenAI capacity, quotas, and best regions for deployment.
Create, validate, and run eval.yaml suites for agent skill evaluation.
Query and analyze logs, telemetry, and time-series data in Azure Data Explorer.
Assess AKS Automatic readiness and generate fixes for migration blockers.
Explore AI models, MCP servers, and agent integrations in one gateway.
Help AI agents discover and run enterprise tools securely.
Expose Azure ML endpoints as MCP tools for natural-language AI agent calls.
Deploy Azure OpenAI models and find regional capacity intelligently.
Give AI real-time Azure infrastructure access for ops checks, policy validation, and Terraform analysis.
Search Azure service updates, retirements, and feature announcements in natural language.