typespec-create-api-plugin

作者: github

为Microsoft 365 Copilot生成包含REST操作、身份验证和自适应卡片的TypeSpec API插件。根据Microsoft 365 Copilot约定,搭建包含代理定义(main.tsp)和API操作(actions.tsp)的完整TypeSpec项目。支持四种身份验证模式:公共API、API密钥标头、OAuth2授权码流程以及注册身份验证引用。包含用于破坏性操作的可选确认对话框以及自适应卡片模板,用于...

npx skills add https://github.com/github/awesome-copilot --skill typespec-create-api-plugin

Create TypeSpec API Plugin

Create a complete TypeSpec API plugin for Microsoft 365 Copilot that integrates with external REST APIs.

Requirements

Generate TypeSpec files with:

main.tsp - Agent Definition

import "@typespec/http";
import "@typespec/openapi3";
import "@microsoft/typespec-m365-copilot";
import "./actions.tsp";

using TypeSpec.Http;
using TypeSpec.M365.Copilot.Agents;
using TypeSpec.M365.Copilot.Actions;

@agent({
  name: "[Agent Name]",
  description: "[Description]"
})
@instructions("""
  [Instructions for using the API operations]
""")
namespace [AgentName] {
  // Reference operations from actions.tsp
  op operation1 is [APINamespace].operationName;
}

actions.tsp - API Operations

import "@typespec/http";
import "@microsoft/typespec-m365-copilot";

using TypeSpec.Http;
using TypeSpec.M365.Copilot.Actions;

@service
@actions(#{
    nameForHuman: "[API Display Name]",
    descriptionForModel: "[Model description]",
    descriptionForHuman: "[User description]"
})
@server("[API_BASE_URL]", "[API Name]")
@useAuth([AuthType]) // Optional
namespace [APINamespace] {
  
  @route("[/path]")
  @get
  @action
  op operationName(
    @path param1: string,
    @query param2?: string
  ): ResponseModel;

  model ResponseModel {
    // Response structure
  }
}

Authentication Options

Choose based on API requirements:

  1. No Authentication (Public APIs)

    // No @useAuth decorator needed
    
  2. API Key

    @useAuth(ApiKeyAuth<ApiKeyLocation.header, "X-API-Key">)
    
  3. OAuth2

    @useAuth(OAuth2Auth<[{
      type: OAuth2FlowType.authorizationCode;
      authorizationUrl: "https://oauth.example.com/authorize";
      tokenUrl: "https://oauth.example.com/token";
      refreshUrl: "https://oauth.example.com/token";
      scopes: ["read", "write"];
    }]>)
    
  4. Registered Auth Reference

    @useAuth(Auth)
    
    @authReferenceId("registration-id-here")
    model Auth is ApiKeyAuth<ApiKeyLocation.header, "X-API-Key">
    

Function Capabilities

Confirmation Dialog

@capabilities(#{
  confirmation: #{
    type: "AdaptiveCard",
    title: "Confirm Action",
    body: """
    Are you sure you want to perform this action?
      * **Parameter**: {{ function.parameters.paramName }}
    """
  }
})

Adaptive Card Response

@card(#{
  dataPath: "$.items",
  title: "$.title",
  url: "$.link",
  file: "cards/card.json"
})

Reasoning & Response Instructions

@reasoning("""
  Consider user's context when calling this operation.
  Prioritize recent items over older ones.
""")
@responding("""
  Present results in a clear table format with columns: ID, Title, Status.
  Include a summary count at the end.
""")

Best Practices

  1. Operation Names: Use clear, action-oriented names (listProjects, createTicket)
  2. Models: Define TypeScript-like models for requests and responses
  3. HTTP Methods: Use appropriate verbs (@get, @post, @patch, @delete)
  4. Paths: Use RESTful path conventions with @route
  5. Parameters: Use @path, @query, @header, @body appropriately
  6. Descriptions: Provide clear descriptions for model understanding
  7. Confirmations: Add for destructive operations (delete, update critical data)
  8. Cards: Use for rich visual responses with multiple data items

Workflow

Ask the user:

  1. What is the API base URL and purpose?
  2. What operations are needed (CRUD operations)?
  3. What authentication method does the API use?
  4. Should confirmations be required for any operations?
  5. Do responses need Adaptive Cards?

Then generate:

  • Complete main.tsp with agent definition
  • Complete actions.tsp with API operations and models
  • Optional cards/card.json if Adaptive Cards are needed

来自 github 的更多技能

console-rendering
github
在Go中使用基于结构体标签的控制台渲染系统的说明
official
acquire-codebase-knowledge
github
当用户明确要求映射、记录或熟悉现有代码库时使用此技能。触发词如“映射此代码库”、“记录…
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
通过AgentRC指令命令生成定制化的AI代理指令文件。生成.github/copilot-instructions.md(默认,推荐用于VS Code中的Copilot…
official
acreadiness-policy
github
帮助用户选择、编写或应用AgentRC策略。策略通过禁用无关检查、覆盖影响/级别、设置…来定制就绪评分。
official
add-educational-comments
github
为代码文件添加教育性注释,将其转化为有效的学习资源。根据三个可配置的知识水平(初级、中级、高级)调整解释深度和语气。若未提供文件,自动请求文件,并附带编号列表以便快速选择。仅通过教育性注释将文件扩展最多125%(硬性限制:新增400行;超过1000行的文件限制为300行)。保留文件编码、缩进风格、语法正确性以及...
official
adobe-illustrator-scripting
github
使用ExtendScript(JavaScript/JSX)编写、调试和优化Adobe Illustrator自动化脚本。在创建或修改操作…的脚本时使用。
official
agent-governance
github
声明式策略、意图分类及审计追踪,用于控制AI代理工具访问与行为。可组合的治理策略定义允许/禁止的工具、内容过滤器、速率限制及审批要求——以配置而非代码形式存储。语义意图分类在执行工具前通过基于模式的信号检测危险提示(数据泄露、权限提升、提示注入)。工具级治理装饰器在函数层面强制执行策略...
official