AI Agents & Automation

Discover and install agent skills from the open ecosystem via the npx skills CLI — when you wish you had a skill for some task.

End-to-end Azure AI Foundry agent lifecycle with azd—scaffold, deploy, invoke, evaluate, optimize, fine-tune, and troubleshoot agents—routing to specialized sub-skills per task.

Fine-tunes models on Azure AI Foundry with SFT, DPO, or RFT, covering dataset prep and validation, grader calibration, training, checkpoint selection, deployment, and evaluation.

Unified Azure OpenAI deployment router that detects intent and dispatches to quick preset, full customize, or capacity-discovery modes, with shared project and quota validation.

Interactive guided Azure OpenAI deployment giving full control over version, SKU, capacity, RAI policy, and advanced options, with cross-region fallback and live quota checks.

Discovers available Azure OpenAI model capacity across all accessible regions and projects, then validates subscription quota and ranks deployment locations.

Quickly deploys an Azure OpenAI model to the optimal region by checking capacity across regions and using GlobalStandard SKU with sensible auto-calculated defaults.

Configures Azure API Management as an AI gateway: token limits, semantic caching, content safety, load balancing, token metrics, and MCP/tool rate limiting via az CLI policies.

Router and reference for Azure AI services (AI Search, Speech, OpenAI, Document Intelligence) covering full-text/vector/hybrid search, speech, and OCR via MCP, CLI, and SDKs.

A bare starter scaffold with empty YAML frontmatter and a placeholder body, meant as a starting point for writing your own skill.

Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources.