Azure Active Directory B2c

> 🚀 Agentic Skills for Azure Development > > Supercharge your AI coding assistant with curated, production-ready skills for Microsoft Azure. Works seamlessly with: > > 🟣 Claude Code | 🔵 Gemini CLI | 🟢 Codex CLI | 🔴 Antigravity IDE | 🩵 GitHub Copilot | 🟠 Cursor | ⚪ OpenCode | 🌸 AdaL CLI

Azure Agent Skills is a curated collection of high-quality agentic skills specifically designed for Azure cloud development. These skills follow the Agent Skills open standard and work seamlessly with modern AI coding assistants to provide expert-level guidance on Azure services.

📍 Table of Contents

• 🚀 New Here? Start Here!
• ⚡ One-Click Plugin Install
• 🔌 Compatibility & Invocation
• 📦 Features & Categories
• 🎁 Curated Collections (Bundles)
• 📚 Browse All Skills
• 🛠️ Installation
• 🧠 How to Use
• 📖 Agent Skills Documentation
• 🤝 How to Contribute
• ⚖️ License

🚀 New Here? Start Here!

1. 🐣 What is this?

AI Agents (like GitHub Copilot, Claude Code, or Cursor) are smart, but they lack specific, up-to-date knowledge about Azure services. Skills are folders containing markdown instructions, scripts, and resources that teach AI agents how to work with Azure services correctly, every time.

> 💡 Skills are reusable, filesystem-based resources that provide AI agents with domain-specific expertise. They load on-demand and eliminate the need to repeatedly provide the same guidance across conversations.

2. 📚 How These Skills Are Created

Microsoft Learn documentation already encodes decisions, procedures, best practices, and constraints — exactly what agents need to act effectively. Rather than relying on RAG to retrieve and summarize raw text every time, we pre-compile this knowledge into structured, executable skills.

Documentation as Pre-Built Skills: Many effective agent skills are not new inventions — they are structured patterns, workflows, and decision logic that already exist in documentation. Consider what Learn content contains:

• API patterns and usage guidance
• Service configuration procedures
• Platform best practices and constraints
• Troubleshooting decision trees
• Security and compliance requirements

Our approach:

1. Extract high-value, task-oriented capabilities from Learn content
2. Classify by purpose (limits, troubleshooting, configuration, architecture, etc.)
3. Reveal only when relevant to the user's intent

The knowledge is pre-compiled into actions, choices, and guardrails the agent can use directly — not raw text that needs interpretation.

Each skill provides:

• 📚 Curated documentation links organized by topic
• 🔗 Direct access to Microsoft Learn content
• 🎯 Best practices and architecture patterns
• ⚠️ Troubleshooting guides and common pitfalls

3. ⚡️ Quick Start

A short path to getting started — full installation details are in the 🛠️ Installation section below.

� Plugin install (recommended): VS Code, Claude Code, and Codex can install everything as a single agent plugin — no cloning or copying.

• VS Code: Command Palette → Chat: Install Plugin From Source → paste https://github.com/MicrosoftDocs/agent-skills
• Claude Code: /plugin marketplace add MicrosoftDocs/agent-skills, then /plugin install azure-agent-skills@microsoft-agent-skills
• Codex: codex plugin marketplace add MicrosoftDocs/agent-skills, then install azure-agent-skills from /plugins

> 👉 See ⚡ One-Click Plugin Install for full steps and the marketplace options.

🛠️ Other assistants (manual):

1. Clone the repo:

   git clone https://github.com/MicrosoftDocs/agent-skills.git

1. Copy the contents of the skills/ folder to your AI assistant's skills path (see 🛠️ Installation for the destination table and important notes).

1. VS Code users (manual mode): enable chat.agent.skills in Settings so the editor will load skills.