About skillsets for Copilot Extensions

Learn what Github Copilot 기술 세트 are and how they simplify integrating third-party tools and functions into your Copilot experience.

이 문서의 내용

A skill within GitHub Copilot is a tool that the model calls to perform a specific task in response to a user query. A skillset is a collection of these skills (up to five per skillset). Github Copilot 기술 세트 provide a streamlined way to extend Copilot’s functionality, allowing builders to integrate external services or custom API endpoints into their Copilot workflow. With skillsets, builders can enable Copilot to perform tasks—such as retrieving data or executing actions in third-party services—without needing to manage complex workflows or architecture.

For a quickstart example of a skillset, see the skillset-example repository. For information on building a skillset, see Building Copilot skillsets.

How skillsets and agents differ

기술 세트와 에이전트는 Copilot 확장성 플랫폼을 통해 Copilot의 기능과 컨텍스트를 확장하는 두 가지 방법입니다. 외부 서비스와 API를 Copilot 채팅에 통합할 수 있지만 각각 다른 사용 사례를 제공하고 다양한 수준의 제어와 복잡성을 제공합니다.

  • 기술 세트는 Copilot가 최소한의 설정으로 특정 작업(예: 데이터 검색이나 간단한 작업)을 수행해야 하는 개발자를 위해 가볍고 간소화되었습니다. 라우팅, 프롬프트 작성, 함수 평가, 응답 생성을 자동으로 처리하므로 빠르고 간단한 통합에 적합합니다.
  • 에이전트는 요청이 처리되고 응답이 생성되는 방식을 완전히 제어해야 하는 복잡한 통합을 위한 것입니다. 사용자 지정 논리를 구현하고, 다른 LLM 및/또는 Copilot API와 통합하고, 대화 컨텍스트를 관리하고, 사용자 상호 작용의 모든 측면을 처리할 수 있습니다. 에이전트는 더 많은 엔지니어링과 유지 관리가 필요하지만, 정교한 워크플로를 위한 최대 유연성을 제공합니다. 에이전트에 대한 자세한 내용은 About agents for Copilot Extensions을(를) 참조하세요.

The extensibility platform

Skillsets and agents both operate on the GitHub Copilot 확장성 플랫폼, which manages the flow of user requests and function evaluations. With Copilot 기술 세트, the platform handles routing, prompt crafting, function calls and prompt generation.

Workflow overview

The extensibility platform follows a structured workflow to process user requests and generate responses:

  1. User request
    A user issues a request in the Copilot 채팅 interface, such as asking for data or executing a specific action.

  2. Routing
    The request is routed to the appropriate extension. For skillsets, this means the platform agent identifies and invokes the corresponding skillset based on the user’s intent. Each skill’s inference description helps the platform determine which skill to call.

  3. Dynamic Prompt Crafting
    GitHub Copilot generates a prompt using:

    • The user’s query.
    • Relevant thread history.
    • Available functions within the skillset.
    • Results from any prior function calls.

  4. LLM Completion
    The language model (LLM) processes the prompt and determines:

    • Whether the user’s intent matches a skillset function.
    • Which function(s) to call and with what arguments.
    • If required, the LLM may send additional function calls to gather more context.

  5. Function Evaluation
    The extension invokes the selected function(s), which may involve:

    • Gathering relevant context, such as Copilot 기술 세트 repository or user metadata.
    • Making an API call to an external service to retrieve data or execute an action.

  6. Response generation The platform iteratively refines the output, looping through prompt crafting, LLM completion, and function evaluation as needed. Once the process is complete, Copilot streams a final response back to the user in the chat interface.