teams-anthropic-patterns

Implement Teams.ai patterns with Anthropic SDK for memory, function calling, and streaming.

25|6|Updated Sep 23, 2025
One-click install
npx skills add https://github.com/youdotcom-oss/dx-toolkit --skill teams-anthropic-patterns
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teams-anthropic-patterns
Source: https://github.com/youdotcom-oss/dx-toolkit/tree/main/.agents/skills/teams-anthropic-patterns
Command: npx skills add https://github.com/youdotcom-oss/dx-toolkit --skill teams-anthropic-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Integrates Teams.ai patterns with Anthropic to enable memory-aware conversations, safe function-calling, and streaming capabilities for Teams.ai apps.

Core Features & Use Cases

  • Memory API patterns to manage conversation state with memory.push() and memory.values().
  • Function-calling and message transformation with consistent message structures and handler-based access.
  • Streaming integration using Anthropic streaming to deliver real-time AI responses in Teams.
  • Debugging guidance and patterns for MCP-based workflows with Anthropic SDK.

Quick Start

Navigate to packages/teams-anthropic and run bun test and bun run check to verify the integration.

Frequently Asked Questions about teams-anthropic-patterns

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

FAQPage Schema
How do I manage conversation state in Teams.ai apps using Anthropic integration?

To manage conversation state in Teams.ai apps using Anthropic integration, you use the Memory API patterns with memory.push() to store context and memory.values() to retrieve conversation state. This ensures durable memory persistence across multi-turn interactions within Microsoft Teams.

Can I stream real-time Anthropic AI responses inside Microsoft Teams?

Yes, you can stream real-time Anthropic AI responses inside Microsoft Teams by implementing the Anthropic streaming APIs within the Teams.ai framework. This pattern delivers real-time, token-by-token AI responses directly to the Teams client interface.

What is the best way to implement function calling with the Anthropic SDK in a Teams bot?

The best way to implement function calling with the Anthropic SDK in a Teams bot is using consistent message structures and handler-based access. This pattern ensures safe, reliable function execution by properly routing function calls through Teams.ai handlers.

How do I debug MCP-based Teams.ai workflows that require memory and function execution?

To debug MCP-based Teams.ai workflows that require memory and function execution, use the provided debugging patterns and tests for the Anthropic SDK. Run bun test and bun run check in the packages/teams-anthropic directory to verify integration and memory adapter behavior.

Does the Teams.ai Anthropic integration support memory adapters for complex conversation state?

Yes, the Teams.ai Anthropic integration supports memory adapters for complex conversation state. These adapters work with the memory API to manage and persist durable conversation context required for advanced, stateful MCP-based Teams applications.