PluginBench
Skill
Official
Review
Audit score 70

typespec-create-agent

github/awesome-copilot

Generate complete TypeSpec declarative agents for Microsoft 365 Copilot with instructions, capabilities, and conversation starters.

What is typespec-create-agent?

This skill generates a fully-formed TypeSpec declarative agent definition for Microsoft 365 Copilot. Use it when you need to create a new agent with custom instructions, capabilities, and conversation starters that guide user interactions.

  • Generates main.tsp files with @agent decorator and metadata
  • Creates behavioral instructions using @instructions decorator (up to 8,000 characters)
  • Adds 2-4 conversation starters with titles and example queries
  • Includes selected capabilities (WebSearch, OneDriveAndSharePoint, TeamsMessages, Email, People, CodeInterpreter, GraphicArt, GraphConnectors, Dataverse, Meetings)
  • Applies scoping to capabilities (URLs, folders) for performance optimization
  • Validates agent names (≤100 chars) and descriptions (≤1,000 chars)

How to install typespec-create-agent

npx skills add https://github.com/github/awesome-copilot --skill typespec-create-agent
Prerequisites
  • TypeSpec compiler installed
  • Access to Microsoft TypeSpec M365 Copilot libraries
  • Understanding of desired agent capabilities and scope
Claude Code
Cursor
Windsurf
Cline

How to use typespec-create-agent

  1. 1.Define the agent's purpose, role, and expertise area
  2. 2.List the specific capabilities the agent needs (WebSearch, OneDriveAndSharePoint, etc.)
  3. 3.Identify knowledge sources and data the agent should access
  4. 4.Describe typical user interactions and use cases
  5. 5.Review generated main.tsp file for accuracy
  6. 6.Deploy to Microsoft 365 Copilot environment

Use cases

Good for
  • Create a customer support agent that searches knowledge bases and accesses Teams channels
  • Build a research assistant with web search and document access capabilities
  • Generate a meeting insights agent that accesses calendar and meeting content
  • Define a data analysis agent with CodeInterpreter and Dataverse access
  • Set up a team collaboration agent with email, Teams, and SharePoint integration
Who it's for
  • Microsoft 365 Copilot developers
  • Enterprise AI platform architects
  • Teams and SharePoint administrators building custom agents
  • Organizations creating domain-specific copilot assistants

typespec-create-agent FAQ

What is the maximum length for agent instructions?

Instructions can be up to 8,000 characters. Use clear, second-person language ("You are...") to define behavior, expertise, and limitations.

How many conversation starters should I include?

Include 2-4 conversation starters. Make them diverse to showcase different agent capabilities and typical user interactions.

Can I limit capability scope?

Yes. Capabilities like WebSearch, OneDriveAndSharePoint, and Email support optional scoping (URLs, folders) for better performance and security.

What capabilities are available?

WebSearch, OneDriveAndSharePoint, TeamsMessages, Email, People, CodeInterpreter, GraphicArt, GraphConnectors, Dataverse, and Meetings.

What are the naming constraints?

Agent names must be 100 characters or less; descriptions must be 1,000 characters or less.

Full instructions (SKILL.md)

Source of truth, from github/awesome-copilot.


name: typespec-create-agent description: 'Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot'

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.