Individual skill
crestapps-core-azure-ai-inference
Skill for using Azure AI Inference, Azure AI Foundry serverless models, and GitHub Models in CrestApps.Core 2.0. Covers AddAzureAIInference and AddCoreAIAzureAIInference registration, connections with the AzureAIInference client name, Endpoint, AuthenticationType (Default, ApiKey, ManagedIdentity) and IdentityId, configured chat and embedding deployments that declare model capabilities through Features and Parameters instead of the removed Purpose or Type, deployment slots resolved with ResolveSlotAsync, per-model capability differences such as tool calling, unsupported image, speech and realtime clients, and upgrading from 1.x. Use it when connecting a CrestApps.Core host to GitHub Models or an Azure AI model catalog endpoint, comparing model families behind one endpoint, or troubleshooting authentication, skipped deployments, or tools that never run.
src/CrestApps.AgentSkills/crestapps-core/crestapps-core-azure-ai-inference/SKILL.md
Source commit d86d04f234b1b2bd8145368a2544490f9d557596
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 13
- Repository last updated
- Oct 21, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai Repository topic
- ai-agents-framework Repository topic
- dotnet Repository topic
- mcp Repository topic
- mcp-server Repository topic
- orchardcore Repository topic
- devops Derived category
- security Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 8,151 bytes
Read excerpt
# CrestApps.Core Azure AI Inference
The `CrestApps.Core.AI.AzureAIInference` package uses the `Azure.AI.Inference` SDK to reach one endpoint that serves many model families (OpenAI, Meta Llama, Mistral, Cohere, and others). It is the provider for GitHub Models and for serverless model deployments in Azure AI Foundry.
## Guidelines
- Use it for multi-model evaluation, GitHub Models prototypes, and serverless Azure model catalog deployments.
- Keep the endpoint and credentials on the connection; keep the model name and its capabilities on the deployment.
- Always set `AuthenticationType`. When it is empty the provider uses `DefaultAzureCredential`, even if `ApiKey` is set. A GitHub token needs `"AuthenticationType": "ApiKey"`.
- Only chat and embeddings are supported. Image generation, speech-to-text, text-to-speech and realtime throw `NotSupportedException`; use `crestapps-core-openai` or `crestapps-core-azure-openai` for those.
- Declare features per model. Tool calling, vision and structured outputs vary across the catalog; declare only what the chosen model supports.
## Registration
