Agent skill
microsoft-foundry-classic
Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents, RAG/vector search, function calling, realtime audio, or fine-tuned Azure OpenAI models, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).
Install this agent skill to your Project
npx add-skill https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/microsoft-foundry-classic
Metadata
Additional technical details for this skill
- generator
- docs2skills/1.0.0
- generated at
- 2026-04-05
SKILL.md
Microsoft Foundry Classic Skill
This skill provides expert guidance for Microsoft Foundry Classic. 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), 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:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetchwith query stringfrom=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpagewith query stringfrom=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L37-L46 | Diagnosing and fixing Foundry issues: prompt flow compute/usage, deployments and monitoring, private endpoints, Azure OpenAI fine-tuning, safety/risk monitoring, and known bugs/workarounds. |
| Best Practices | L47-L61 | Best practices for prompts, safety, fine-tuning (incl. vision), latency/cost optimization, DeepSeek-R1 use, On Your Data, and evaluating/improving Foundry/Azure OpenAI chat apps |
| Decision Making | L62-L93 | Guidance for choosing and upgrading models, regions, SDKs, and deployment types, managing versions, costs, PTU, and migrations to plan and operate Foundry-based AI solutions. |
| Architecture & Design Patterns | L94-L104 | Architectural guidance for Foundry: multi-agent design, service/resource topology, high availability, and full BCDR (backup, recovery, DR, and resiliency) for Agent Service and Azure OpenAI workloads |
| Limits & Quotas | L105-L120 | Quotas, rate limits, and capacity for Foundry Agents/Models and Azure OpenAI (deployments, regions, VNets, batch, dynamic quota, fine-tuning, and retired/available models). |
| Security | L121-L168 | Security, networking, auth, RBAC, keys, policies, guardrails, content safety, and data privacy for Foundry hubs/projects, tools, and Azure OpenAI/Direct model integrations |
| Configuration | L169-L226 | Configuring, monitoring, and evaluating Foundry agents/models: infra and networking, BYO resources, tools and evaluators, RAG/vector indexes, safety/filters, logging, tracing, and Azure OpenAI settings. |
| Integrations & Coding Patterns | L227-L351 | Patterns and code to integrate Foundry and Azure OpenAI with tools, data sources, and frameworks: search/RAG, function calling, agents, evaluations, realtime audio, and fine-tuning. |
| Deployment | L352-L371 | Deploying Foundry hubs, projects, and models (managed/serverless), configuring regions, agents, CI/CD (GitHub/Azure DevOps), and using Bicep/Terraform/CLI/portal for deployment. |
Troubleshooting
| Topic | URL |
|---|---|
| Troubleshoot compute and usage issues in prompt flow | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-troubleshoot |
| Troubleshoot Foundry deployments and monitoring issues | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-deploy-and-monitor |
| Troubleshoot Foundry private endpoint connection errors | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-secure-connection-project |
| Troubleshoot Azure OpenAI fine-tuning issues in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-troubleshoot |
| Monitor and troubleshoot Risks & Safety in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor |
| Resolve known issues and workarounds in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/reference/foundry-known-issues |
Best Practices
Decision Making
Architecture & Design Patterns
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
azure-blueprints
Expert knowledge for Azure Blueprints development including troubleshooting, architecture & design patterns, security, configuration, and integrations & coding patterns. Use when defining Azure Blueprints, mapping built-in compliance sets, automating via CLI/PowerShell/REST, or fixing assignment errors, and other Azure Blueprints related development tasks. Not for Azure Policy (use azure-policy), Azure Resource Manager (use azure-resource-manager), Azure Managed Applications (use azure-managed-applications), Azure Deployment Environments (use azure-deployment-environments).
azure-hdinsight
Expert knowledge for Azure HDInsight development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when working with HDInsight Spark/Hive/Kafka/HBase clusters, Ambari, VNet networking, or Azure SQL/Cosmos DB integration, and other Azure HDInsight related development tasks. Not for Azure Synapse Analytics (use azure-synapse-analytics), Azure Databricks (use azure-databricks), Azure Stream Analytics (use azure-stream-analytics).
azure-advisor
Expert knowledge for Azure Advisor development including best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when configuring Advisor alerts, workbooks, RBAC access, bulk fixes, or Resource Graph/Kusto queries, and other Azure Advisor related development tasks. Not for Azure Cost Management (use azure-cost-management), Azure Monitor (use azure-monitor), Azure Policy (use azure-policy), Azure Service Health (use azure-service-health).
azure-cognitive-search
Expert knowledge for Azure AI Search development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing indexes/skillsets, vector/semantic search, indexers, RAG knowledge bases, or secure data access, and other Azure AI Search related development tasks. Not for Azure Cosmos DB (use azure-cosmos-db), Azure Data Explorer (use azure-data-explorer), Azure SQL Database (use azure-sql-database), Azure Synapse Analytics (use azure-synapse-analytics).
azure-migrate
Expert knowledge for Azure Migrate development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AppCAT/CAST, Site Recovery REST APIs, Azure Migrate appliance, Arc-based discovery, or Resource Mover, and other Azure Migrate related development tasks. Not for Azure Database Migration service (use azure-database-migration), Azure Site Recovery (use azure-site-recovery), Azure Virtual Machines (use azure-virtual-machines), SQL Server on Azure Virtual Machines (use azure-sql-virtual-machines).
azure-maps
Expert knowledge for Azure Maps development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when using Azure Maps web SDK, search/geocoding, routing/traffic, weather APIs, or migrating from Bing/Google Maps, and other Azure Maps related development tasks.
Didn't find tool you were looking for?