Microsoft Foundry
Skill Verifiziert AktivDeploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve agent instructions, optimize system prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
To enable developers to efficiently deploy, evaluate, and manage AI agents within the Microsoft Foundry ecosystem, covering the full development lifecycle.
Funktionen
- Orchestrates Foundry agent deployment workflows (build, push, create, start)
- Supports agent evaluation, batch eval, and continuous monitoring
- Facilitates prompt optimization and agent instruction tuning
- Manages dataset curation from traces and dataset versioning
- Provides SDK guides for Python, .NET, TypeScript, and Java
Anwendungsfälle
- Deploying a new agent to Microsoft Foundry
- Evaluating agent performance against custom datasets
- Troubleshooting deployment failures for Foundry agents
- Optimizing agent prompts for better performance
Nicht-Ziele
- General Azure deployments outside of Foundry
- Deploying to Azure Functions or App Service
- Building or managing Azure infrastructure unrelated to Foundry agents
Scope
- info:Tool surface sizeThe `microsoft-foundry` skill itself acts as a router, delegating to numerous sub-skills and MCP tools, rather than exposing a large number of its own direct tools.
Installation
Zuerst Marketplace hinzufügen
/plugin marketplace add microsoft/skills/plugin install azure-skills@skillsQualitätspunktzahl
VerifiziertVertrauenssignale
Ähnliche Erweiterungen
Azure Servicebus Py
100Azure Service Bus SDK for Python messaging. Use for queues, topics, subscriptions, and enterprise messaging patterns. Triggers: "service bus", "ServiceBusClient", "queue", "topic", "subscription", "message broker".
Azure Monitor Query Py
100Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics. Triggers: "azure-monitor-query", "LogsQueryClient", "MetricsQueryClient", "Log Analytics", "Kusto queries", "Azure metrics".
Azure Container Registry SDK for Python
100Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories. Triggers: "azure-containerregistry", "ContainerRegistryClient", "container images", "docker registry", "ACR".
Azure App Configuration SDK for Python
100Azure App Configuration SDK for Python. Use for centralized configuration management, feature flags, and dynamic settings. Triggers: "azure-appconfiguration", "AzureAppConfigurationClient", "feature flags", "configuration", "key-value settings".
Context Compression
100This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Azure Deploy
100Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.