typespec-create-agent — GitHub Copilot skill: build an agent
This skill drafts a TypeSpec definition for a Microsoft 365 Copilot declarative agent. Use it to shape the agent's instructions, capabilities, and sample prompts.
npx skills add github/awesome-copilot --skill typespec-create-agentWhat typespec-create-agent does
The skill generates a main.tsp file with an agent declaration, behavioral instructions, and conversation starters. You can provide two to four starters and choose capabilities to match the agent's needs.
Available capabilities cover web search, OneDrive and SharePoint documents, Teams messages, and email. The list also includes organization people search, Python execution, image generation, Dataverse, meetings, and Copilot connector content. Sources can be scoped by URL or folder where supported. Install it when you're building for Microsoft 365 Copilot; it is a poor fit for a general-purpose chatbot prompt.
What it helps with
- draft an agent definition in
main.tsp - set the agent's role and behavioral limits
- choose capabilities for the agent's data sources
- add varied conversation starters
Example prompts for the agent
- Create an agent that answers employee questions using OneDrive documents.
- Generate `main.tsp` for an agent that searches Teams messages and email.
- Draft a declarative agent with web search and Python execution.
How to install typespec-create-agent
1Skills CLI (Vercel)
npx skills add github/awesome-copilot --skill typespec-create-agent2GitHub CLI
gh skill install github/awesome-copilot typespec-create-agent3Manually: put the files in place
.github/skills/typespec-create-agent/SKILL.md1Skills CLI (Vercel)
npx skills add github/awesome-copilot --skill typespec-create-agent -a claude-code2Manually: put the files in place
~/.claude/skills/typespec-create-agent/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/typespec-create-agent/
Manually: put the files in place
.agents/skills/typespec-create-agent/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/typespec-create-agent/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
Platform CLI
gemini skills install https://github.com/github/awesome-copilot --path skills/typespec-create-agentManually: put the files in place
.devin/skills/typespec-create-agent/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set554
The whole set →Similar
Questions about typespec-create-agent
How do I install typespec-create-agent in GitHub Copilot?
Run npx skills add github/awesome-copilot --skill typespec-create-agent or gh skill install github/awesome-copilot typespec-create-agent.
What does typespec-create-agent do?
It generates a main.tsp definition for a Microsoft 365 Copilot declarative agent, with instructions, conversation starters, and selected capabilities.
Which capabilities can the agent use?
Options include web search, OneDrive and SharePoint access, Teams messages, and email. Choose only the capabilities the agent needs.
Source text
SKILL.md · MIT
---
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
```typescript
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.
© github · MIT · github/awesome-copilot