From azure-agent-skills
Provides expert guidance for Microsoft Foundry (Azure AI Foundry) development including troubleshooting, best practices, architecture patterns, security, and deployment. Use when building Foundry agents with Azure OpenAI/Claude, VNet isolation, model routing, or M365/Teams integration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/azure-agent-skills:microsoft-foundryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides expert guidance for Microsoft Foundry. 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.
This skill provides expert guidance for Microsoft Foundry. 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.
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L37-L45 | Diagnosing and recovering from Foundry model/agent failures, evaluation and observability issues, webhook problems, and known service bugs with workarounds. |
| Best Practices | L46-L59 | Best practices for prompts, tools, safety messages, routing, evaluation, and fine-tuning so you can design, operate, and measure high-quality Azure/Foundry AI agents in production |
| Decision Making | L60-L95 | Guides for choosing models, deployments, regions, costs, and lifecycle policies, plus planning migrations (classic, GitHub, Azure OpenAI), DR, and optimal agent/model configuration. |
| Architecture & Design Patterns | L96-L102 | Designing Foundry agent architectures: VNet/subnet sizing, isolated resource layouts, high availability patterns, and model router patterns for routing and scaling AI workloads. |
| Limits & Quotas | L103-L123 | Quotas, limits, regions, and rate caps for Foundry models, agents, sessions, Azure OpenAI, Claude, batch, caching, and tools to size, control, and safeguard usage and costs |
| Security | L124-L160 | Security, identity, and compliance for Foundry: auth/RBAC, agent identities, private networking, guardrails/safety, data privacy, keys, policies, and securing MCP/Agent 365 access. |
| Configuration | L161-L220 | Configuring Foundry agents, models, tools, security, networking, monitoring, and evaluations, including Azure OpenAI, Fireworks, tracing, guardrails, and automation workflows. |
| Integrations & Coding Patterns | L221-L303 | Patterns and code to integrate Foundry agents/models with tools, data, gateways, observability, LangChain/LangGraph, Azure OpenAI features, fine-tuning, and real-time/Responses APIs. |
| Deployment | L304-L324 | Deploying and publishing Foundry agents and models (hosted, containerized, voice, VNet), integrating with M365/Teams/DevOps, and running cloud evaluations and red-teaming. |
| Topic | URL |
|---|---|
| Troubleshoot and understand Foundry partner models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners |
| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery |
| Troubleshoot Foundry evaluation and observability issues | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/troubleshooting |
| Set up and troubleshoot Azure OpenAI webhooks | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks |
| Known issues and workarounds for Microsoft Foundry services | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |
| Topic | URL |
|---|---|
| Design networking and subnet sizing for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agents-networking-deep-dive |
| Plan standard agent setup with isolated resources | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup |
| Design high availability for Microsoft Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency |
npx claudepluginhub microsoftdocs/agent-skills --plugin azure-agent-skillsProvides expert guidance for Microsoft Foundry Classic (Azure AI Foundry) development: troubleshooting, best practices, architecture, deployment, and integrations for agents, RAG/search, tools, and model routing.
Deploys, evaluates, fine-tunes, and manages Microsoft Foundry agents end-to-end using azd. Covers hosted agent scaffold, prompt creation, batch eval, continuous eval, and agent optimization.
Build AI agents and applications on Microsoft Foundry using the azure-ai-projects Python SDK. Supports OpenAI-compatible clients, agent CRUD, tools like code interpreter, evaluations, and datasets.