microsoft-foundry

The Microsoft Foundry skill provides a framework for the end-to-end lifecycle of AI agents, including scaffolding, deployment, evaluation, fine-tuning, and troubleshooting within Azure AI Foundry.

429.2K
Installs
7
Use cases
5/10
Quality

Is microsoft-foundry safe to install?

Review the source first

Review the source first: our audit of microsoft-foundry's source files found 1 shell command, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands via azd and reads/writes local configuration files within the .foundry workspace directory.

How we audit skills: our security review methodology.

Who is this skill for?

Developers building, deploying, and managing AI agents on Azure AI Foundry.

What can you do with it?

  • Deploying hosted agents to Foundry
  • Creating and updating prompt agents
  • Evaluating agent quality and running batch evaluations
  • Optimizing agent prompts and instructions
  • Fine-tuning models using SFT, DPO, or RFT
  • Troubleshooting agent deployment failures and logs
  • Managing Azure AI Foundry project infrastructure and RBAC

How good is this skill?

Quality score: 5/10. The skill documentation is comprehensive, clearly defining sub-skills, infrastructure lifecycle, and workspace standards. It provides explicit instructions on tool usage and context resolution.

What does the skill file contain?

SKILL.md
# 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 discovery/help step for MCP-based workflows.

## Sub-Skills

> **MANDATORY: Before executing ANY workflow-specific steps, you MUST read the corresponding sub-skill document.** Do not call workflow-...

Frequently asked questions

How do I start a new agent project?

Use the create/quick-start-hosted sub-skill for an end-to-end scaffold, provision, and deploy flow.

Where should I store agent-specific metadata?

Store Foundry-specific cache and overlay state in the .foundry/ directory within the agent root folder.

How do I optimize an existing agent's prompt?

Load the observe sub-skill and use the prompt_optimize MCP tool.

What should I do before executing a specific workflow?

Read the corresponding sub-skill document to ensure all pre-checks and validation logic are followed.

Data sourced from microsoft/azure-skills on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

developing-genkit-js

50.1K

Developers building AI agents, flows, and tools using the Genkit framework in JavaScript or TypeScript environments

This skill provides guidance for developing AI-powered applications using Genkit in Node.js and TypeScript. It enforces a strict troubleshooting protocol that prioritizes reading local documentation via the Genkit CLI over internal knowledge to account for recent breaking API changes.

highGenkitTypeScriptgenkit-ai

marketingskills-ai-agents

1.3K

Developers and marketers using AI coding agents who want to automate marketing tasks, content generation, and site optimization

A collection of 33 markdown-based AI agent skills designed to provide marketing expertise, including CRO, copywriting, SEO, analytics, and growth engineering, for coding agents like Claude Code.

highmarketingseoaradotso

seo-geo-claude-skills

941

SEO professionals, content strategists, and developers using AI coding agents to automate search engine optimization workflows

A library of 20 specialized SEO and GEO skills for AI coding agents, organized into research, build, optimize, monitor, and cross-cutting phases. It utilizes CORE-EEAT and CITE frameworks for content and authority benchmarking.

highSEOGEOaradotso

ai-marketing-skills-automation

640

Marketing teams and developers using AI coding agents like Claude Code to automate growth, sales, and content workflows

A collection of Python-based automation scripts for marketing operations, including growth experiments, sales pipeline management, content quality scoring, outbound email generation, SEO analysis, and financial cost auditing.

highmarketing-automationpythonaradotso