Login
Officialmicrosoft/azure-skillsMIT195 files

Microsoft Foundry

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Use this skillView repositoryView on skills.sh
Specification
Skill ID
microsoft/azure-skills/microsoft-foundry
Publisher
microsoft
Repository
azure-skills
Installs
2,469
Files
195
License
MIT
Synced
Sep 16, 2026
How to use it

Open any RiverX project, open the Skills panel in the chat, and search for this identifier. The files are fetched from the source repository at install time.

microsoft/azure-skills/microsoft-foundryInstalls these files
  • .gitignore
  • SKILL.md
  • finetuning/SKILL.md
  • finetuning/references/agentic-rft.md
  • finetuning/references/dataset-formats.md
  • finetuning/references/deployment.md
  • finetuning/references/evaluation.md
  • finetuning/references/grader-design.md
  • finetuning/references/hyperparameters.md
  • finetuning/references/large-file-uploads.md
  • finetuning/references/platform-gotchas.md
  • finetuning/references/reward-hacking.md
  • finetuning/references/training-curves.md
  • finetuning/references/training-types.md
  • finetuning/references/vision-fine-tuning.md
  • finetuning/scripts/calibrate_grader.py
  • finetuning/scripts/check_training.py
  • finetuning/scripts/cleanup.py
  • finetuning/scripts/common.py
  • finetuning/scripts/convert_dataset.py
  • finetuning/scripts/deploy_model.py
  • finetuning/scripts/evaluate_model.py
  • finetuning/scripts/generate_distillation_data.py
  • finetuning/scripts/monitor_training.py
  • finetuning/scripts/score_dataset.py
  • finetuning/scripts/submit_training.py
  • finetuning/scripts/validate/__init__.py
  • finetuning/scripts/validate/data_stats.py
  • finetuning/scripts/validate/validate_dpo.py
  • finetuning/scripts/validate/validate_rft.py
  • finetuning/scripts/validate/validate_sft.py
  • finetuning/workflows/dataset-creation.md
  • finetuning/workflows/diagnose-poor-results.md
  • finetuning/workflows/full-pipeline.md
  • finetuning/workflows/iterative-training.md
  • finetuning/workflows/quickstart.md
  • foundry-agent/agent-optimizer/agent-optimizer.md
  • foundry-agent/agent-optimizer/references/azd-setup.md
  • foundry-agent/agent-optimizer/references/eval-yaml.md
  • foundry-agent/agent-optimizer/references/optimize-workflow.md
  • foundry-agent/agent-optimizer/references/python-patterns.md
  • foundry-agent/agent-optimizer/references/scaffold.md
  • foundry-agent/azd-guidance/azd-guidance.md
  • foundry-agent/azd-guidance/references/azd-ai-cli.md
  • foundry-agent/cicd/cicd.md
  • foundry-agent/create/create-hosted.md
  • foundry-agent/create/create-prompt.md
  • foundry-agent/create/quick-start-hosted.md
  • foundry-agent/create/references/enable-incoming-a2a.md
  • foundry-agent/create/references/foundry-model.md
  • foundry-agent/create/references/foundry-tool-catalog.md
  • foundry-agent/create/references/guardrails/guardrail-api-create.md
  • foundry-agent/create/references/guardrails/guardrail-attach.md
  • foundry-agent/create/references/guardrails/guardrail-manage.md
  • foundry-agent/create/references/langchain-langgraph-hosting.md
  • foundry-agent/create/references/local-run.md
  • foundry-agent/create/references/re-host.md
  • foundry-agent/create/references/sdk-operations.md
  • foundry-agent/create/references/skills/skill-attach.md
  • foundry-agent/create/references/skills/skill-manage.md
  • foundry-agent/create/references/skills/skill-toolbox-attach.md
  • foundry-agent/create/references/tools/prompt-agent/agent-tools.md
  • foundry-agent/create/references/tools/prompt-agent/tool-a2a.md
  • foundry-agent/create/references/tools/prompt-agent/tool-azure-ai-search.md
  • foundry-agent/create/references/tools/prompt-agent/tool-bing-grounding.md
  • foundry-agent/create/references/tools/prompt-agent/tool-code-interpreter.md
  • foundry-agent/create/references/tools/prompt-agent/tool-fabric-iq.md
  • foundry-agent/create/references/tools/prompt-agent/tool-file-search.md
  • foundry-agent/create/references/tools/prompt-agent/tool-function-calling.md
  • foundry-agent/create/references/tools/prompt-agent/tool-mcp.md
  • foundry-agent/create/references/tools/prompt-agent/tool-memory.md
  • foundry-agent/create/references/tools/prompt-agent/tool-openapi.md
  • foundry-agent/create/references/tools/prompt-agent/tool-web-search.md
  • foundry-agent/create/references/tools/prompt-agent/tool-work-iq.md
  • foundry-agent/create/references/use-toolbox-in-hosted-agent.md
  • foundry-agent/create/scripts/check-copilot-app-entry.ps1
  • foundry-agent/create/scripts/check-copilot-app-entry.sh
  • foundry-agent/create/scripts/resolve-project-id.ps1
  • foundry-agent/create/scripts/resolve-project-id.sh
  • foundry-agent/create/scripts/verify-environment.ps1
  • foundry-agent/create/scripts/verify-environment.sh
  • foundry-agent/deploy/deploy.md
  • foundry-agent/deploy/references/container-deploy.md
  • foundry-agent/eval-datasets/eval-datasets.md
  • foundry-agent/eval-datasets/references/dataset-comparison.md
  • foundry-agent/eval-datasets/references/dataset-curation.md
  • foundry-agent/eval-datasets/references/dataset-organization.md
  • foundry-agent/eval-datasets/references/dataset-versioning.md
  • foundry-agent/eval-datasets/references/eval-lineage.md
  • foundry-agent/eval-datasets/references/eval-regression.md
  • foundry-agent/eval-datasets/references/eval-trending.md
  • foundry-agent/eval-datasets/references/generate-seed-dataset.md
  • foundry-agent/eval-datasets/references/trace-to-dataset.md
  • foundry-agent/insights/insights.md
  • foundry-agent/insights/references/tool-contract.md
  • foundry-agent/invocations-ws/invocations-ws.md
  • foundry-agent/invocations-ws/references/invocations-ws-protocol.md
  • foundry-agent/invoke/invoke.md
  • foundry-agent/invoke/references/file-operations.md
  • foundry-agent/invoke/references/invocations-protocol.md
  • foundry-agent/invoke/references/session-management.md
  • foundry-agent/observe/observe.md
  • foundry-agent/observe/references/analyze-results.md
  • foundry-agent/observe/references/cicd-monitoring.md
  • foundry-agent/observe/references/compare-iterate.md
  • foundry-agent/observe/references/continuous-eval.md
  • foundry-agent/observe/references/deploy-and-setup.md
  • foundry-agent/observe/references/evaluate-step.md
  • foundry-agent/observe/references/evaluation-suite-generation.md
  • foundry-agent/observe/references/optimize-deploy.md
  • foundry-agent/routine/references/azure-yaml.md
  • foundry-agent/routine/references/cli-crud.md
  • foundry-agent/routine/routine.md
  • foundry-agent/toolbox/references/mcp-protocol.md
  • foundry-agent/toolbox/references/test-endpoint.md
  • foundry-agent/toolbox/references/tool-a2a.md
  • foundry-agent/toolbox/references/tool-azure-ai-search.md
  • foundry-agent/toolbox/references/tool-browser-automation.md
  • foundry-agent/toolbox/references/tool-code-interpreter.md
  • foundry-agent/toolbox/references/tool-fabric-iq.md
  • foundry-agent/toolbox/references/tool-file-search.md
  • foundry-agent/toolbox/references/tool-mcp-agent-identity.md
  • foundry-agent/toolbox/references/tool-mcp-custom-oauth-azure-starter.md
  • foundry-agent/toolbox/references/tool-mcp-custom-oauth.md
  • foundry-agent/toolbox/references/tool-mcp-key-auth.md
  • foundry-agent/toolbox/references/tool-mcp-managed-oauth.md
  • foundry-agent/toolbox/references/tool-mcp-noauth.md
  • foundry-agent/toolbox/references/tool-mcp-user-entra-token.md
  • foundry-agent/toolbox/references/tool-openapi.md
  • foundry-agent/toolbox/references/tool-tool-search.md
  • foundry-agent/toolbox/references/tool-web-search.md
  • foundry-agent/toolbox/references/tool-work-iq.md
  • foundry-agent/toolbox/references/toolbox-azd.md
  • foundry-agent/toolbox/scripts/get-catalog-inputs.ps1
  • foundry-agent/toolbox/scripts/get-catalog-inputs.sh
  • foundry-agent/toolbox/toolbox.md
  • foundry-agent/trace/references/analyze-failures.md
  • foundry-agent/trace/references/analyze-latency.md
  • foundry-agent/trace/references/conversation-detail.md
  • foundry-agent/trace/references/eval-correlation.md
  • foundry-agent/trace/references/kql-templates.md
  • foundry-agent/trace/references/search-traces.md
  • foundry-agent/trace/trace.md
  • foundry-agent/troubleshoot/troubleshoot.md
  • foundry-agent/validate/references/default-rules.yaml
  • foundry-agent/validate/references/report-schema.json
  • foundry-agent/validate/references/report-template.md.tpl
  • foundry-agent/validate/references/rules-schema.json
  • foundry-agent/validate/validate.md
  • models/deploy-model/SKILL.md
  • models/deploy-model/TEST_PROMPTS.md
  • models/deploy-model/capacity/SKILL.md
  • models/deploy-model/capacity/scripts/discover_and_rank.ps1
  • models/deploy-model/capacity/scripts/discover_and_rank.sh
  • models/deploy-model/capacity/scripts/query_capacity.ps1
  • models/deploy-model/capacity/scripts/query_capacity.sh
  • models/deploy-model/customize/EXAMPLES.md
  • models/deploy-model/customize/SKILL.md
  • models/deploy-model/customize/references/customize-guides.md
  • models/deploy-model/customize/references/customize-workflow.md
  • models/deploy-model/preset/EXAMPLES.md
  • models/deploy-model/preset/SKILL.md
  • models/deploy-model/preset/references/preset-workflow.md
  • models/deploy-model/preset/references/workflow.md
  • models/deploy-model/scripts/generate_deployment_url.ps1
  • models/deploy-model/scripts/generate_deployment_url.sh
  • project/connections.md
  • project/create/create-foundry-project.md
  • quota/quota.md
  • quota/references/capacity-planning.md
  • quota/references/error-resolution.md
  • quota/references/optimization.md
  • quota/references/ptu-guide.md
  • quota/references/troubleshooting.md
  • quota/references/workflows.md
  • rbac/rbac.md
  • references/agent-metadata-contract.md
  • references/auth-best-practices.md
  • references/standard-agent-setup.md
  • resource/create/create-foundry-resource.md
  • resource/create/references/patterns.md
  • resource/create/references/troubleshooting.md
  • resource/create/references/workflows.md
  • resource/private-network/private-network.md
  • resource/private-network/references/custom-template-adaptation.md
  • resource/private-network/references/deploy.md
  • resource/private-network/references/end-to-end-test.md
  • resource/private-network/references/intake.md
  • resource/private-network/references/post-deployment-validation.md
  • resource/private-network/references/scaffold.md
  • resource/private-network/references/template-index.md
  • resource/private-network/references/vpn-dns-setup.bicep
  • resource/private-network/references/vpn-dns-setup.md
  • scripts/check-and-setup-dependencies.ps1
  • scripts/check-and-setup-dependencies.sh

What this skill tells the agent

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-SkillWhen to UseReference
deployDeploy hosted agents to Foundry, smoke-test a deployment, create or update prompt agents, and manage agent versions and multi-environment deploys.deploy
cicdSet up a CI/CD deployment pipeline for a Foundry agent.cicd
invokeSend messages to an agent, single or multi-turn conversationsinvoke
routineSchedule 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-wsBuild, 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
observeEvaluate agent quality, run batch evals, analyze failures, optimize prompts, improve agent instructions, compare versions, set up CI/CD monitoring, and enable continuous production evaluationobserve
insightsPull generated agent insights, evidence, and recommendations from an existing monitor; read-only retrieval, not a new analysis runinsights
traceQuery traces, analyze latency/failures, correlate eval results to specific responses via App Insights customEventstrace
troubleshootView hosted agent logs, query telemetry, diagnose failurestroubleshoot
validateUse 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
createUse 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-optimizerMake 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-datasetsHarvest 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/createCreating 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/createCreating 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-networkAnswer 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-modelUnified 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
quotaManaging 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
rbacManaging 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
finetuningFine-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-guidanceProvide shared azd knowledge and guidance for managing Foundry agents. Read this first for any workflows related to azd.azd-guidance

More from microsoft

microsoft/azure-skills

Azure Prepare

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.

microsoft/azure-skills

Azure Compliance

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.

microsoft/azure-skills

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.