microsoft-foundry
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment,
Profile →npx skills add microsoft/skills --skill microsoft-foundry --agent copilot
Same command for any agent — swap --agent for claude-code, codex, cursor.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides end-to-end management of Microsoft Foundry agents: deploying hosted agents, creating prompt agents, running and evaluating agents, maintaining CI/CD, optimizing prompts and agent instructions, and handling model fine-tuning (SFT/DPO/RFT). It includes workflows for dataset curation from traces, agent optimizer scaffolding, and agent deployment through azd. It supports RBAC and region/capacity considerations, along with provisioning Foundry resources and governance tasks.
How it works
The skill prescribes a set of mandatory setup steps and sub-skills to follow before workflows:
- Run dependency checks and setup scripts from the skill root:
./scripts/check-and-setup-dependencies.shor./scripts/check-and-setup-dependencies.ps1. - Read the corresponding sub-skill document before executing any workflow-specific steps.
- Use the Azure MCP
foundrytool for MCP discovery of available tools and parameters. - Before any
azdcommand, readazd-guidanceand follow theAZURE_DEV_USER_AGENTrules. - Engage the relevant sub-skills for desired tasks, such as
deployfor hosting agents,observefor evaluation and prompt optimization,agent-optimizerfor optimization of hosted-agent code,eval-datasetsfor dataset management, andfinetuningfor model customization. - Follow the Agent Development Lifecycle: start with dependency/setup, then azd-guidance, then the appropriate workflow (e.g., quick-start-hosted, deploy, invoke, observe, troubleshoot, etc.).
- Use
azdand Foundry workflows to scaffold, provision, deploy, invoke, evaluate, monitor, and optimize agents, with explicit routing through the recommended sub-skills.
When to use it
Use when deploying hosted Foundry agents, creating or updating prompt agents, performing batch or continuous evaluations, configuring and running CI/CD for agents, optimizing prompts and agent instructions, or performing model fine-tuning (SFT/DPO/RFT). It also covers dataset curation from traces and RBAC/permissions setup.
What it can touch
The skill references tooling and workflows including:
azdcommands for provisioning and deploying Foundry resources and agents.foundryMCP tools for discovery of MCP-based workflows.- Scripts under
scripts/for dependency checks. - Sub-skills like
deploy,observe,agent-optimizer,eval-datasets,finetuning,cicd,invoke,routine,troubleshoot(as applicable per task).
Caveats
- Mandatory dependency check must complete before any sub-skill use.
- Mandatory reading of the corresponding sub-skill document before workflow execution.
- Azure Dev user agent rules must be followed when using azd commands.
- The skill operates within the Foundry resource and agent lifecycle; no guarantees beyond described steps are provided. License: MIT.
# 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 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
What does the microsoft-foundry skill do?
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment,
How do I install it?
Run `npx skills add microsoft/skills --skill microsoft-foundry --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From microsoft/skills, a repository with 2,860 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.