typespec-create-agent

作者: github

为Microsoft 365 Copilot生成一个完整的TypeSpec声明式代理,包含指令、功能和对话启动器。生成一个main.tsp文件,其中包含代理声明、指令、对话启动器以及遵循Microsoft TypeSpec M365 Copilot模式的功能定义。支持10种功能类型,包括WebSearch、OneDriveAndSharePoint、TeamsMessages、Email、People、CodeInterpreter、GraphicArt、GraphConnectors、Dataverse和Meetings,并支持可选的范围限定...

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

Create TypeSpec Declarative Agent

Create a complete TypeSpec declarative agent for Microsoft 365 Copilot with the following structure:

Requirements

Generate a main.tsp file with:

  1. Agent Declaration

    • Use @agent decorator with a descriptive name and description
    • Name should be 100 characters or less
    • Description should be 1,000 characters or less
  2. Instructions

    • Use @instructions decorator with clear behavioral guidelines
    • Define the agent's role, expertise, and personality
    • Specify what the agent should and shouldn't do
    • Keep under 8,000 characters
  3. Conversation Starters

    • Include 2-4 @conversationStarter decorators
    • Each with a title and example query
    • Make them diverse and showcase different capabilities
  4. Capabilities (based on user needs)

    • WebSearch - for web content with optional site scoping
    • OneDriveAndSharePoint - for document access with URL filtering
    • TeamsMessages - for Teams channel/chat access
    • Email - for email access with folder filtering
    • People - for organization people search
    • CodeInterpreter - for Python code execution
    • GraphicArt - for image generation
    • GraphConnectors - for Copilot connector content
    • Dataverse - for Dataverse data access
    • Meetings - for meeting content access

Template Structure

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

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

@agent({
  name: "[Agent Name]",
  description: "[Agent Description]"
})
@instructions("""
  [Detailed instructions about agent behavior, role, and guidelines]
""")
@conversationStarter(#{
  title: "[Starter Title 1]",
  text: "[Example query 1]"
})
@conversationStarter(#{
  title: "[Starter Title 2]",
  text: "[Example query 2]"
})
namespace [AgentName] {
  // Add capabilities as operations here
  op capabilityName is AgentCapabilities.[CapabilityType]<[Parameters]>;
}

Best Practices

  • Use descriptive, role-based agent names (e.g., "Customer Support Assistant", "Research Helper")
  • Write instructions in second person ("You are...")
  • Be specific about the agent's expertise and limitations
  • Include diverse conversation starters that showcase different features
  • Only include capabilities the agent actually needs
  • Scope capabilities (URLs, folders, etc.) when possible for better performance
  • Use triple-quoted strings for multi-line instructions

Examples

Ask the user:

  1. What is the agent's purpose and role?
  2. What capabilities does it need?
  3. What knowledge sources should it access?
  4. What are typical user interactions?

Then generate the complete TypeSpec agent definition.

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