skills.rest
AcendWay
AcendWayCOMMUNITY
Explore all skills by this author →
GitHub

microsoft-foundry

Orchestrate Microsoft Foundry agent deployments, invocations, and evaluation workflows.

Updated May 25, 2026
Search Tags:#prompt optimization#agent deployment#azure ai foundry#evaluation and monitoring#quota and capacity#rbac permissions#trace to dataset
One-click install
npx skills add https://github.com/AcendWay/ai-skills-library --skill microsoft-foundry-acendway
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: microsoft-foundry
Source: https://github.com/AcendWay/ai-skills-library/tree/main/skill-folders/microsoft-foundry
Command: npx skills add https://github.com/AcendWay/ai-skills-library --skill microsoft-foundry-acendway

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates fragmented, error-prone setup work by giving a single operational guide for deploying, invoking, evaluating, monitoring, and troubleshooting Microsoft Foundry agents and related infrastructure.

Core Features & Use Cases

  • Agent lifecycle orchestration: create, deploy, invoke, troubleshoot, and redeploy Foundry agents (prompt and hosted) with clear routing to purpose-built sub-skills.
  • Eval-driven quality improvement: build/refresh evaluation datasets, run batch evaluations, analyze failures, optimize prompts/instructions, compare versions, and enable continuous monitoring.
  • Infrastructure essentials: create Foundry projects/resources, handle RBAC, quota/capacity decisions, and deploy models with intelligent routing—while enforcing pre-flight discovery rules (MCP tool discovery and sub-skill document reads).

Quick Start

Deploy a Foundry hosted agent using the microsoft-foundry skill, then immediately invoke it and run evals to spot optimization opportunities.

Frequently Asked Questions about microsoft-foundry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy and evaluate Foundry agents end-to-end?▼

To deploy and evaluate Foundry agents, you can orchestrate project provisioning, containerized hosted agent deploys, and batch evaluations within a single workflow. This includes model routing, agent invocations, and continuous monitoring to ensure quality.

What is the best way to run batch evaluations on Azure AI Foundry agents?▼

The best way to run batch evaluations on Azure AI Foundry agents is by building evaluation datasets and running continuous evaluations to analyze failures. This process enables prompt optimization and version comparison for eval-driven quality improvement.

How do I handle RBAC permissions and quota capacity for Foundry projects?▼

Handling RBAC permissions and quota capacity for Foundry projects involves configuring access controls and resource limits during infrastructure provisioning. This ensures secure, cache-safe artifact persistence and intelligent model routing.

Can I optimize prompts and trace agent invocations in Azure AI Foundry?▼

Yes, you can optimize prompts and trace agent invocations in Azure AI Foundry by utilizing trace-to-dataset pipelines. This allows you to analyze invocation failures, compare versions, and refine instructions for better agent performance.

Why does Foundry agent deployment require MCP discovery and sub-skill document reads?▼

Foundry agent deployment requires MCP discovery and sub-skill document reads to eliminate fragmented setup and enforce pre-flight rules. This ensures consistent selection of agent root, metadata, and environment for cache-safe artifact persistence.

Related Skills

Explore More Software Engineering Skills→
mahmoud20138mahmoud20138
10

microsoft-foundry:microsoft-foundry

Manage Azure AI Foundry agents, models, quotas, and RBAC via Azure CLI.

Community
Advanced
muratcankoylanmuratcankoylan
17.7k

reasoning-trace-optimizer

Analyze interleaved thinking traces to detect failure patterns and optimize prompts.

Community
Advanced
forgefabrikforgefabrik

microsoft-foundry

Orchestrate Microsoft Foundry agent, model, project, and evaluation operations.

Community
Advanced
ammonfifeammonfife

microsoft-foundry

Deploy, evaluate, and optimize AI agents in Microsoft Foundry.

Community
Advanced