What problem does it solve? Building AI agents from scratch requires implementing orchestration, tool invocation, file editing, and model management yourself. This Skill guides you through embedding the production-tested GitHub Copilot agent runtime directly into your own applications using the Copilot SDK, so you define agent behavior while Copilot handles planning and execution. ## Core Features & Use Cases - Multi-language integration: Create agentic sessions in TypeScript, Python, Go, or .NET with streaming responses, session persistence, and multi-turn conversations. - Custom tools and MCP servers: Define tools the agent can invoke during reasoning, and connect to Model Context Protocol servers like the GitHub MCP server for repository, issue, and PR access. - Custom agents and system messages: Configure specialized AI personas and system prompts for tasks like PR review or domain-specific assistance. - Use Case: Build an interactive CLI weather assistant where the Copilot agent calls your custom get_weather tool, streams responses token by token, and maintains conversation context across turns. ## Quick Start Use the copilot-sdk skill to create a TypeScript application that starts a Copilot session with streaming enabled and asks the agent a question.
