microsoft-foundry

Everything you do with an AI agent on Microsoft's Foundry platform after the idea: build it, put it live, ask it things, score its answers, and work out why it went wrong.

WHEN TO USE

SCOPE

USE FOR

Scaffold a new hosted Foundry agent and deploy it end to end with azd.
Evaluate an agent's quality with batch evals and catch regressions before they ship.
Optimize an agent's prompt or instructions using eval-driven feedback.
Set up a CI/CD pipeline that redeploys and re-evaluates a Foundry agent on every change.
Diagnose why a deployed Foundry agent or model deployment is failing.

NOT FOR

Deploy to Azure Functions or App Service — use azure-deploy instead.
Do general Azure resource preparation outside Foundry — use azure-prepare instead.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (13)

Microsoft Foundry Skill

This skill helps developers work with Microsoft Foundry resources, covering model discovery and deployment, complete dev lifecycle of AI agent, evaluation workflows, and troubleshooting.

Pre-Execution Requirements

Follow each applicable subsection below before starting its corresponding action or workflow.

Dependency Check and Setup

MANDATORY: As the first step after this skill loads, run the dependency check and setup script below from this skill's root and wait for it to finish before continuing. The script checks first and installs only missing dependencies; it does not reinstall dependencies that are already available.

You MUST complete this check before reading or entering any sub-skill, workflow, or workflow-specific reference.

./scripts/check-and-setup-dependencies.sh     # macOS / Linux
./scripts/check-and-setup-dependencies.ps1    # Windows (pwsh)

Strictly follow the script output for subsequent actions.

Workflow Guidance

MANDATORY: Before executing ANY workflow-specific steps, you MUST read the corresponding sub-skill document. Do not call workflow-specific MCP tools for a workflow without reading its skill document. This applies even if you already know the MCP tool parameters — the skill document contains required workflow steps, pre-checks, and validation logic that must be followed. This rule applies on every new user message that triggers a different workflow, even if the skill is already loaded.

Foundry MCP

MANDATORY: Before using Foundry MCP operations, call the Azure MCP foundry tool and inspect the available Foundry MCP tools and related parameters. Treat this as the discovery/help step for MCP-based workflows.

azd

MANDATORY: Before executing ANY azd command, you MUST read azd-guidance and strictly follow the shared rules defined in it, especially the AZURE_DEV_USER_AGENT setting rules.

Sub-Skills

This skill includes specialized sub-skills for specific workflows. When a sub-skill matches the task, strictly follow its workflow:

Sub-Skill	When to Use	Reference
deploy	Deploy hosted agents to Foundry, smoke-test a deployment, create or update prompt agents, and manage agent versions and multi-environment deploys.	deploy
cicd	Set up a CI/CD deployment pipeline for a Foundry agent.	cicd
invoke	Send messages to an agent, single or multi-turn conversations	invoke
routine	Schedule or event-trigger Foundry agents with routines; use `azd` for CRUD, enable/disable, manual dispatch, and viewing past runs, or define routines in `azure.yaml`.	routine
invocations-ws	Build, deploy, and connect to hosted agents that speak the `invocations_ws` duplex WebSocket protocol — voice agents, real-time streams, and signaling for out-of-band media transports.	invocations-ws
observe	Evaluate agent quality, run batch evals, analyze failures, optimize prompts, improve agent instructions, compare versions, set up CI/CD monitoring, and enable continuous production evaluation	observe
trace	Query traces, analyze latency/failures, correlate eval results to specific responses via App Insights `customEvents`	trace
troubleshoot	View hosted agent logs, query telemetry, diagnose failures	troubleshoot
validate	Use only when the user explicitly asks to use this validation sub-skill or to validate Microsoft Foundry hosted-agent code against best practices. Never invoke it proactively or add it to another workflow.	validate
create (quick start)	Create a new hosted Foundry agent from scratch end-to-end — scaffold, provision or use an existing Foundry project, deploy, and smoke-test. Do not use for any work on existing code. For anything not covered by the quickstart, use create.	create/quick-start-hosted.md
create	Use when the standard end-to-end happy path (quick start) doesn't fit. Create a new Foundry agent, update code of an existing agent, continue development of an existing agent, wire connections at scaffold time, use advanced setup or A2A (Agent2Agent), or recover from a failed quickstart run.	create
agent-optimizer	Make existing Python hosted-agent code optimization-ready, configure eval.yaml, run Agent Optimizer jobs, apply candidates locally, and deploy through azd after review.	agent-optimizer
eval-datasets	Harvest production traces into evaluation datasets, manage dataset versions and splits, track evaluation metrics over time, detect regressions, and maintain full lineage from trace to deployment. Use for: create dataset from traces, dataset versioning, evaluation trending, regression detection, dataset comparison, eval lineage.	eval-datasets
project/create	Creating a new Microsoft Foundry project for hosting agents and models. Use when onboarding to Foundry or setting up new infrastructure.	project/create/create-foundry-project.md
resource/create	Creating Azure AI Services multi-service resource (Foundry resource) using Azure CLI. Use when manually provisioning AI Services resources with granular control.	resource/create/create-foundry-resource.md
private-network	Answer questions about Foundry network isolation and deploy Foundry with VNet isolation (BYO VNet, Managed VNet, hybrid). Covers architecture concepts, template selection, deployment, and post-deployment validation.	resource/private-network/private-network.md
models/deploy-model	Unified model deployment with intelligent routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI), and capacity discovery across regions. Routes to sub-skills: `preset` (quick deploy), `customize` (full control), `capacity` (find availability).	models/deploy-model/SKILL.md
quota	Managing quotas and capacity for Microsoft Foundry resources. Use when checking quota usage, troubleshooting deployment failures due to insufficient quota, requesting quota increases, or planning capacity.	quota/quota.md
rbac	Managing RBAC permissions, role assignments, managed identities, and service principals for Microsoft Foundry resources. Use for access control, auditing permissions, and CI/CD setup.	rbac/rbac.md
finetuning	Fine-tune models on Microsoft Foundry — SFT distillation, DPO preference optimization, RFT with graders and tool calling. Dataset preparation, grader calibration, training, checkpoint selection, deployment, evaluation. Use for: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, large file upload.	finetuning/SKILL.md
azd-guidance	Provide shared azd knowledge and guidance for managing Foundry agents. Read this first for any workflows related to azd.	azd-guidance

💡 Tip: For a complete onboarding flow: project/create (public) or private-network (VNet isolation) → models/deploy-model → agent workflows (create → deploy → invoke).

💡 Fine-Tuning: Use finetuning for all model customization — SFT distillation, DPO preference optimization, and RFT with graders. Includes quickstart, grader calibration, and training curve analysis.

💡 Model Deployment: Use models/deploy-model for all deployment scenarios — it intelligently routes between quick preset deployment, customized deployment with full control, and capacity discovery across regions.

💡 Prompt Optimization: For requests like "optimize my prompt" or "improve my agent instructions," load observe and use the prompt_optimize MCP tool through that eval-driven workflow.

Infrastructure Lifecycle

Match user intent to the correct infrastructure workflow.

User Intent	Workflow
"Create Foundry" / "Set up Foundry" (ambiguous)	Use `AskUserQuestion`: (a) just an AI Services resource, (b) a project with public access, or (c) a project with network isolation? Route: (a) → resource/create, (b) → project/create, (c) → private-network
Set up Foundry with VNet isolation	private-network
Create a Foundry project (public)	project/create
Create a bare Foundry resource	resource/create

Agent Development Lifecycle

Match user intent to the correct agent workflow. Read each sub-skill in order before executing.

User Intent	Workflow (read in order)
Create a new hosted agent end-to-end (scaffold + deploy + test)	dependency check and setup → azd-guidance → quick-start-hosted (self-contained end-to-end)
Anything beyond the standard quickstart (existing code, migration, re-hosting, deployment customization, scaffold-time connections, A2A (Agent2Agent), recovery)	dependency check and setup → azd-guidance → create → deploy → invoke
Optimize existing Python hosted agent	dependency check and setup → azd-guidance → agent-optimizer → scaffold/review → eval.yaml → optimize → apply candidate → deploy → invoke
Deploy an agent (code already exists)	dependency check and setup → azd-guidance → deploy (includes eval-suite setup) → invoke → observe (evaluate/optimize)
Update/redeploy an agent after code changes	dependency check and setup → azd-guidance → deploy (includes eval-suite setup) → invoke → observe (evaluate/optimize)
Set up a CI/CD deployment pipeline for a hosted agent	dependency check and setup → azd-guidance → cicd
Invoke/test/chat with an agent	dependency check and setup → azd-guidance → invoke
Schedule/event-trigger an agent, or CRUD/enable/disable/dispatch a routine	dependency check and setup → azd-guidance → routine
Optimize / improve agent prompt or instructions	observe (Step 4: Optimize)
Evaluate and optimize agent (full loop)	observe
Enable continuous evaluation monitoring	observe (Step 6: CI/CD & Monitoring)
Troubleshoot an agent issue	dependency check and setup → azd-guidance → invoke → troubleshoot
Fix a broken agent (troubleshoot + redeploy)	dependency check and setup → azd-guidance → invoke → troubleshoot → apply fixes → deploy → invoke

Agent: .foundry Workspace Standard

Every agent source folder can keep Foundry-specific cache and overlay state under .foundry/:

<agent-root>/
  .foundry/
    agent-metadata.yaml
    agent-metadata.prod.yaml
    suites/
    datasets/
    evaluators/
    results/

In azd projects, derive deployment context (project endpoint, agent name/version, ACR, App Insights) from azure.yaml plus azd env get-values; do not duplicate those values in metadata when azd already provides them.
agent-metadata.yaml is the preferred local/dev overlay for non-azd values, remote Foundry suite references, local cache paths, result summaries, and explicit overrides. Optional sidecar files such as agent-metadata.prod.yaml can hold a single prod or CI-targeted overlay without mixing multiple environments in one file.
suites/, datasets/, and evaluators/ are local cache folders. Reuse them when they are current, and ask before refreshing or overwriting them.
See Agent Metadata Contract for the canonical schema and workflow rules.

Agent: Setup References

Standard Agent Setup — advanced setup for production workloads that need data-residency control (bring-your-own Cosmos DB / Storage / AI Search via a Foundry capability host). The default azd ai agent flow uses Basic Agent Setup and does not provision capabilityHosts/agents — do not flag its absence as a bug. For default post-provision state, see the "Expected env-var fingerprint" section in foundry-agent/create/create-hosted.md.

Agent: Common Project Context Resolution

Agent skills should run this step only when they need configuration values they don't already have. If a value (for example, agent root, environment, project endpoint, or agent name) is already known from the user's message or a previous skill in the same session, skip resolution for that value.

Step 1: Discover Agent Roots and azd Context

First check whether the workspace has azure.yaml with services using host: azure.ai.agent.

One azd agent service -> use that service's project folder as the agent root.
Multiple azd agent services -> require the user to choose the target service/folder.
No azd agent service -> search the workspace for .foundry/ folders that contain agent-metadata.yaml or agent-metadata.<env>.yaml.
- One match -> use that agent root.
- Multiple matches -> require the user to choose the target agent folder.
- No matches -> for create/deploy workflows, seed a new .foundry/ folder during setup; for all other workflows, stop and ask the user which agent source folder to initialize.

After selecting an agent root, keep all local .foundry cache inspection, source inspection, evaluator suggestions, dataset suggestions, and prompt-optimization context inside that folder only. Do not scan sibling agent folders unless the user explicitly switches roots.

Step 2: Resolve Environment and Deployment Context

If azure.yaml is present, resolve the azd environment first:

Environment explicitly named by the user
AZURE_ENV_NAME from azd env get-values
azd default environment from .azure/config.json
Environment already selected earlier in the session

Run azd env get-values for the selected environment when project/deployment values are not already known. Prefer azd values for deployment context:

azd Variable	Resolves To
`AZURE_AI_PROJECT_ENDPOINT` or `AZURE_AIPROJECT_ENDPOINT`	Project endpoint
`AGENT_<SERVICE>_NAME`	Agent name for the selected azd service
`AGENT_<SERVICE>_VERSION`	Agent version for the selected azd service
`AZURE_CONTAINER_REGISTRY_NAME` or `AZURE_CONTAINER_REGISTRY_ENDPOINT`	ACR registry name / image URL prefix
`APPLICATIONINSIGHTS_CONNECTION_STRING`	App Insights connection string for trace workflows
`AZURE_SUBSCRIPTION_ID`, `AZURE_RESOURCE_GROUP`, `AZURE_AI_ACCOUNT_NAME`, `AZURE_AI_PROJECT_NAME`	Azure resource lookup and Playground links

When azd supplies these values, use them as the source of truth and do not copy them into .foundry/agent-metadata*.yaml on metadata writes.

Step 3: Select Metadata Overlay and Resolve Environment

Inside the selected agent root, choose the metadata file in this order:

Metadata filename or path explicitly provided by the user or workflow
If an explicit environment is already known and .foundry/agent-metadata.<env>.yaml exists, use that file
.foundry/agent-metadata.yaml
If multiple metadata files remain and no rule above selects one, prompt the user to choose

Read the selected metadata file and resolve any remaining environment choice in this order:

Environment explicitly named by the user
If the selected metadata file defines exactly one environment, use it
Environment already selected earlier in the session
defaultEnvironment from metadata

If the selected metadata file still contains multiple environments and none of the rules above selects one, prompt the user to choose. Keep the selected agent root, metadata file, environment, and whether context came from azd or metadata visible in every workflow summary.

If the selected environment exposes older testSuites[] metadata but not evaluationSuites[], treat testSuites[] as the source for this session and normalize each entry in memory to the evaluationSuites[] shape before continuing. If the metadata is older still and only exposes legacy testCases[], normalize that list the same way. Preserve dataset and evaluator fields, keep any existing tags, and map legacy priority to tags.tier only when tags.tier is missing: P0 -> smoke, P1 -> regression, P2 -> coverage.

Step 4: Resolve eval.yaml Local Evaluation Intent

If eval.yaml exists in the selected agent root, parse it before generating new suites:

agent.name -> target agent candidate; verify it matches the selected azd/metadata agent before using it.
dataset.local_uri -> local seed dataset candidate; legacy dataset_file may be normalized in memory.
dataset.name / dataset.version -> registered dataset candidate.
validation_dataset -> optional validation dataset candidate.
evaluators[] -> candidate Foundry evaluator names; verify with evaluator_catalog_get before treating them as remote evaluators.
name -> local eval/suite candidate; verify remotely before persisting as suiteName.
options.eval_model, options.optimization_model, options.max_candidates, options.optimization_config.model_search_space, options.pass_threshold, max_samples, trace_days, and generation_instruction -> setup defaults.

Treat eval.yaml as local evaluation intent, not proof that a Foundry suite exists. Persist synced suite/dataset/evaluator references to .foundry only after remote lookup or registration succeeds.

Step 5: Resolve Common Configuration

Layer sources in this order:

Explicit user input and values already selected in the session
azd environment values for deployment context
.foundry/agent-metadata*.yaml overlay values and remote suite/cache references
azure.yaml and eval.yaml local source configuration
User prompts for anything still missing

If azd and metadata both provide the same value and they differ, stop and ask which source is authoritative. If they match, use the azd value and avoid rewriting the duplicate on future metadata writes.

Effective Value	Preferred Source	Used By
Project endpoint	azd env	deploy, invoke, observe, trace, troubleshoot
Agent name/version	azd agent variables, then `azure.yaml`	invoke, observe, trace, troubleshoot
ACR	azd env	deploy
Evaluation suites and cache paths	`.foundry/agent-metadata*.yaml`	observe, eval-datasets
Local seed dataset/evaluator intent	`eval.yaml`	observe, eval-datasets

Step 6: Write Metadata Overlay (Create/Deploy/Observe Only)

On any metadata write (deploy, auto-setup, dataset refresh, or trace-to-dataset update), persist only non-derivable overlay/cache state in the selected metadata file:

azd binding (azd.environmentName, azd.service) when useful for future resolution
evaluationSuites[] with remote suite/dataset/evaluator references and local cache paths
lastEval, result files, comparison summaries, or explicit non-azd overrides

Do not copy azd-owned deployment values into metadata when azd already provides them. If the selected file is a preferred single-environment file, rewrite only that one environment block. If the selected file is a legacy multi-environment file, rewrite only the selected environment block. Never copy or merge environments across sibling metadata files automatically. If the selected environment still uses older testSuites[] or legacy testCases[], rewrite it to evaluationSuites[] and remove migrated priority fields from the rewritten entries.

Step 7: Collect Missing Values

Use the ask_user or askQuestions tool only for values not resolved from the user's message, session context, metadata, or azd bootstrap. Common values skills may need:

Agent root — Target azd service project folder or folder containing .foundry/agent-metadata*.yaml
Metadata file — agent-metadata.yaml for local/dev, or an explicit sidecar such as agent-metadata.prod.yaml
Environment — azd environment, dev, prod, or another environment key from metadata
Project endpoint — Microsoft Foundry project endpoint URL
Agent name — Name of the target agent

💡 Tip: If the user already provides the agent path, environment, project endpoint, or agent name, extract it directly — do not ask again.

Agent: Agent Types

All agent skills support two agent types:

Type	Kind	Description
Prompt	`"prompt"`	LLM-based agents backed by a model deployment
Hosted	`"hosted"`	Container-based agents running custom code

Treat an azure.yaml service with host: azure.ai.agent as Hosted. Use agent_get only when the type cannot be resolved from project context.

Tool Usage Conventions

Use the ask_user or askQuestions tool whenever collecting information from the user
Use the task or runSubagent tool to delegate long-running or independent sub-tasks (e.g., env var scanning, status polling, Dockerfile generation)
Prefer azd for Hosted Agents and Foundry MCP for Prompt Agents.
Reference official Microsoft documentation URLs instead of embedding CLI command syntax

Azure Authentication

Azure Authentication Best Practices

Additional Resources

Network Isolation Errors

Applies to any call against a Foundry project or its parent Foundry account — Foundry MCP tools, azd, az CLI, curl, REST, or SDK.

If an error matches Public access is disabled / PublicNetworkAccessDisabled / 403 Forbidden from a private endpoint / connection timeout / the project endpoint FQDN resolves to a public IP, this typically means the parent Foundry account has publicNetworkAccess=Disabled or Enabled from selected IP addresses, and the current shell is outside its VNet.

Only if the error is ambiguous, confirm against the Foundry account using a management-plane call (works from anywhere with reader access):

az cognitiveservices account show \
  --name <account> --resource-group <rg> \
  --query "properties.{publicNetworkAccess:publicNetworkAccess, networkAcls:networkAcls, privateEndpointConnections:privateEndpointConnections[].properties.privateLinkServiceConnectionState.status}"

publicNetworkAccess: "Disabled" — or "Enabled" together with non-empty networkAcls.ipRules / virtualNetworkRules — confirms isolation. If publicNetworkAccess: "Enabled" and networkAcls is empty, the failure is a caller-side network issue (e.g. Private DNS resolving the FQDN to a public IP from inside a VNet with a private endpoint), not an account-config issue.

If it's indeed a network isolation issue, supported connection options are documented in Choose a secure connection method to Foundry.

ℹ️ Foundry MCP tools cannot reach a VNet-isolated project even from inside the VNet.

This skill ships inside the Azure Skills Plugin. Listed package contents include hooks and an MCP server. Installed components and skill versions may vary by AI tool.

Run this outside your AI tool, using Node.js 22.20.0 or newer. Skills CLI 1.7.2 skips skill selection; prompts cancel installation without an interactive terminal. If choosing Project when asked about installation scope, open your project's folder before running this.

Install checklist

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add microsoft/azure-skills --skill "microsoft-foundry" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

Some steps also need an MCP server

Some steps call for tools from the Azure MCP Server; the rest don't. Installing just this skill doesn't add that connection; for those steps, set it up in your AI tool if it isn't there yet: Microsoft's Azure MCP Server guide.

Requirements for the Azure MCP Server

It needs Node.js when you set it up with npm or npx, one of several ways to install it.
It acts with your own Azure sign-in, for example through az login, and what it can do follows your Azure role assignments (RBAC).

What's inside

Files included with this skill.

View on GitHub

Same repository

airunway-aks-setup
Set up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: "setup AI Runway", "onboard AKS cluster", "install AI Runway", "airunway setup", "deploy model to AKS", "GPU inference on AKS", "KAITO setup on AKS", "run LLM on AKS", "vLLM on AKS", "set up model serving on AKS", "AI Runway controller".Read full description
appinsights-instrumentation
Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.Read full description
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.Read full description
azure-aigateway
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.Read full description
azure-app-onboard
End-to-end orchestrator: from a business idea, app idea, or existing app to running Azure deployment with cost estimates and pre-deploy approval. Analyzes your app, auto-detects the right Azure services, scaffolds infrastructure code, and deploys — tailored to your app, not a template. Handles moving existing apps to Azure without rewriting or with minimal changes. WHEN: bring your app to Azure, plan my app, cost to run, is my code ready to deploy, deploy my app to the cloud, deploy all my services, what Azure services do I need, plan my Azure deployment, deploy my new app to Azure, one-click deploy, I have an app and want it on Azure, migrate my app to Azure, help me get started, build an app, no code yet, starter project. DO NOT USE FOR: use azd for deployment(use azure-deploy), optimizing existing costs (use cost-optimization), code readiness checks only (use azure-app-onboard-prereq).Read full description
azure-app-onboard-prereq
Assess whether source code is ready to deploy to Azure — the check BEFORE infrastructure work. Evaluates build health, app completeness, dependencies and local services, stack compatibility, and deployment feasibility. Answers questions about what your app needs before it can be deployed — frameworks, dependencies, and configuration. Checks whether dependencies are compatible and identifies deployment blockers and unsupported frameworks. WHEN: \"evaluate my repo\", \"is my app ready to deploy\", \"what does my app need to deploy\", \"what do I need before deploying\", \"does my app need\", \"can I ship this to Azure\", \"scan my repo for issues\", \"is this app deployable\", \"check if my app is ready for Azure\", \"do I need a Dockerfile\", \"what's blocking my deployment\", \"are there any blockers\", \"are my dependencies compatible\", \"does Azure support my framework\", \"what needs to change before deploying\", \"check my app configuration\".Read full description