### AI Setup Prompt for Trigger.dev

Source: https://trigger.dev/docs/quick-start

This prompt guides AI assistants through the process of adding Trigger.dev to your project. It covers account creation, SDK initialization, MCP server installation, dev server startup, task testing, secret key configuration, and triggering tasks from backend code. It also specifies critical rules for SDK usage, such as always importing from '@trigger.dev/sdk' and never using 'client.defineJob()'.

```text
Help me add Trigger.dev to this project.

## What to do

1. I need a Trigger.dev account. If I don't have one, point me to https://cloud.trigger.dev to sign up. Wait for me to confirm.
2. Run `npx trigger.dev@latest init` in the project root.
     - When it asks about the MCP server, recommend I install it (best DX: gives you direct access to Trigger.dev docs, deploys, and run monitoring).
     - Install the "Hello World" example task when prompted.
3. Run `npx trigger.dev@latest dev` to start the dev server.
4. Once the dev server is running, test the example task from the Trigger.dev dashboard.
5. Set TRIGGER_SECRET_KEY in my .env file (or .env.local for Next.js). I can find it on the API Keys page in the dashboard.
6. Ask me what framework I'm using and show me how to trigger the task from my backend code.

If I've already run init and want the MCP server, run: npx trigger.dev@latest install-mcp

## Critical rules

- ALWAYS import from `@trigger.dev/sdk`. NEVER import from `@trigger.dev/sdk/v3`.
- NEVER use `client.defineJob()` — that's the deprecated v2 API.
- Use type-only imports when triggering from backend code to avoid bundling task code:

    import type { myTask } from "./trigger/example";
    import { tasks } from "@trigger.dev/sdk";

    const handle = await tasks.trigger<typeof myTask>("hello-world", { message: "Hello from my app!" });

## When done, point me to

- Writing tasks: https://trigger.dev/docs/tasks/overview
- Real-time updates: https://trigger.dev/docs/realtime/overview
- AI tooling: https://trigger.dev/docs/building-with-ai

```

--------------------------------

### AI Setup Prompt for Trigger.dev

Source: https://trigger.dev/docs/llms-full.txt

This prompt can be used with AI coding assistants to automate the setup of Trigger.dev in your project. It guides the AI through account creation, SDK initialization, task installation, dev server startup, and environment variable configuration.

```text
Help me add Trigger.dev to this project.

## What to do

1. I need a Trigger.dev account. If I don't have one, point me to https://cloud.trigger.dev to sign up. Wait for me to confirm.
2. Run `npx trigger.dev@latest init` in the project root.
   - When it asks about the MCP server, recommend I install it (best DX: gives you direct access to Trigger.dev docs, deploys, and run monitoring).
   - Install the "Hello World" example task when prompted.
3. Run `npx trigger.dev@latest dev` to start the dev server.
4. Once the dev server is running, test the example task from the Trigger.dev dashboard.
5. Set TRIGGER_SECRET_KEY in my .env file (or .env.local for Next.js). I can find it on the API Keys page in the dashboard.
6. Ask me what framework I'm using and show me how to trigger the task from my backend code.

If I've already run init and want the MCP server, run: npx trigger.dev@latest install-mcp

## Critical rules

- ALWAYS import from `@trigger.dev/sdk`. NEVER import from `@trigger.dev/sdk/v3`.
- NEVER use `client.defineJob()` — that's the deprecated v2 API.
- Use type-only imports when triggering from backend code to avoid bundling task code:

    import type { myTask } from "./trigger/example";
    import { tasks } from "@trigger.dev/sdk";

    const handle = await tasks.trigger<typeof myTask>("hello-world", { message: "Hello from my app!" });

## When done, point me to

- Writing tasks: https://trigger.dev/docs/tasks/overview
- Real-time updates: https://trigger.dev/docs/realtime/overview
- AI tooling: https://trigger.dev/docs/building-with-ai

```

--------------------------------

### Install MCP Client (opencode)

Source: https://trigger.dev/docs/mcp-introduction

Install the MCP client for opencode using the command line.

```bash
npx trigger.dev@latest install-mcp --client opencode
```

--------------------------------

### Start Webapp Service

Source: https://trigger.dev/docs/open-source-self-hosting

Run the start script with the 'webapp' argument to initiate the web application service.

```bash
./start.sh webapp
```

--------------------------------

### Initialize Trigger.dev CLI

Source: https://trigger.dev/docs/guides/frameworks/nodejs

Use this command to add Trigger.dev to your project, create a `/trigger` folder, and set up an example task. It also handles logging in and installing necessary SDK packages.

```bash
npx trigger.dev@latest init
```

```bash
pnpm dlx trigger.dev@latest init
```

```bash
yarn dlx trigger.dev@latest init
```

--------------------------------

### Install MCP Client (AMP)

Source: https://trigger.dev/docs/mcp-introduction

Install the MCP client for AMP using the command line.

```bash
npx trigger.dev@latest install-mcp --client amp
```

--------------------------------

### Install MCP Client (Ruler)

Source: https://trigger.dev/docs/mcp-introduction

Install the MCP client for Ruler using the command line.

```bash
npx trigger.dev@latest install-mcp --client ruler
```

--------------------------------

### Starting Development Servers

Source: https://trigger.dev/docs/llms-full.txt

Run both your Next.js development server and the Trigger.dev development environment concurrently. This setup is crucial for local testing and debugging.

```bash
npm run dev
npx trigger.dev@latest dev
```

--------------------------------

### Initialize Trigger.dev Project (npm)

Source: https://trigger.dev/docs/guides/frameworks/drizzle

Use this command to add Trigger.dev to your project, create a /trigger folder, and set up an example task. It also prompts for MCP server installation and CLI login.

```bash
npx trigger.dev@latest init
```

--------------------------------

### Install MCP Client (Crush)

Source: https://trigger.dev/docs/mcp-introduction

Install the MCP client for Crush using the command line.

```bash
npx trigger.dev@latest install-mcp --client crush
```

--------------------------------

### Initialize Trigger.dev Project (pnpm)

Source: https://trigger.dev/docs/guides/frameworks/drizzle

Use this command to add Trigger.dev to your project, create a /trigger folder, and set up an example task. It also prompts for MCP server installation and CLI login.

```bash
pnpm dlx trigger.dev@latest init
```

--------------------------------

### Create .env File

Source: https://trigger.dev/docs/open-source-self-hosting

Copies the example environment file to create a new .env file for configuration.

```bash
cp .env.example .env
```

--------------------------------

### Quick Start Helm Installation

Source: https://trigger.dev/docs/self-hosting/kubernetes

Install Trigger.dev using the Helm chart with default values for testing purposes. Ensure you have Helm 3.8+ and kubectl configured.

```bash
helm upgrade -n trigger --install trigger \
  oci://ghcr.io/triggerdotdev/charts/trigger \
  --version "~4.0.0" \
  --create-namespace
```

--------------------------------

### Full Customer Onboarding Workflow in Trigger.dev

Source: https://trigger.dev/docs/migration-n8n

This example demonstrates a complete customer onboarding workflow, translating a multi-step n8n process into a single Trigger.dev task. It includes provisioning, sending emails, notifications, delays, and activation checks.

```typescript
import { task, wait } from "@trigger.dev/sdk";
import { provisionAccount } from "./provision-account";
import { sendWelcomeEmail } from "./send-welcome-email";

export const onboardCustomer = task({
  id: "onboard-customer",
  retry: {
    maxAttempts: 3,
  },
  run: async (payload: {
    customerId: string;
    email: string;
    plan: "starter" | "pro" | "enterprise";
  }) => {
    // provision their account, throws if the subtask fails
    await provisionAccount
      .triggerAndWait({
        customerId: payload.customerId,
        plan: payload.plan,
      })
      .unwrap();

    // send welcome email
    await sendWelcomeEmail
      .triggerAndWait({
        customerId: payload.customerId,
        email: payload.email,
      })
      .unwrap();

    // notify the team
    await notifySlack(`New customer: ${payload.email} on ${payload.plan}`);

    // wait 3 days, then check if they've activated
    await wait.for({ days: 3 });

    const activated = await checkActivation(payload.customerId);
    if (!activated) {
      await sendActivationNudge(payload.email);
    }

    return { customerId: payload.customerId, activated };
  },
});
```

```typescript
import { onboardCustomer } from "@/trigger/onboard-customer";

await onboardCustomer.trigger({
  customerId: customer.id,
  email: customer.email,
  plan: customer.plan,
});
```

--------------------------------

### Python Document to Markdown Conversion Example

Source: https://trigger.dev/docs/llms-full.txt

An example demonstrating how to convert documents to markdown using Python and the MarkItDown library with Trigger.dev. This snippet is illustrative and requires the MarkItDown library to be installed.

```python
# Example usage of MarkItDown with Trigger.dev
# Ensure you have installed the library: pip install markitdown

from markitdown import convert_to_markdown

def convert_document_to_markdown(document_content):
    """Converts a given document content to markdown format."""
    return convert_to_markdown(document_content)

# Example usage:
# html_content = "<h1>Hello World</h1><p>This is a test.</p>"
# markdown_output = convert_document_to_markdown(html_content)
# print(markdown_output)

```

--------------------------------

### Initialize and Start Resource Monitor

Source: https://trigger.dev/docs/llms-full.txt

This snippet shows how to initialize the ResourceMonitor class and start monitoring system resources at a specified interval. It includes middleware setup and conditional enabling via environment variables.

```typescript
import { task, logger, wait } from "@trigger.dev/sdk";
import { ResourceMonitor } from "../resourceMonitor.js";

// Middleware to enable the resource monitor
tasks.middleware("resource-monitor", async ({ ctx, next }) => {
  const resourceMonitor = new ResourceMonitor({
    ctx,
  });

  // Only enable the resource monitor if the environment variable is set
  if (process.env.RESOURCE_MONITOR_ENABLED === "1") {
    resourceMonitor.startMonitoring(1_000);
  }

  await next();

  resourceMonitor.stopMonitoring();
});

export const resourceMonitorTest = task({
  id: "resource-monitor-test",
  run: async (payload: any, { ctx }) => {
    const interval = createMemoryPressure();

    await setTimeout(180_000);

    clearInterval(interval);

    return {
      message: "Hello, resources!",
    };
  },
});
```

--------------------------------

### Install MCP for All Supported Clients

Source: https://trigger.dev/docs/mcp-introduction

Use this command to install the MCP into all supported clients automatically. This is a convenient way to set up the MCP across your development environment.

```bash
npx trigger.dev@latest install-mcp --yolo
```

--------------------------------

### Basic Playwright Setup

Source: https://trigger.dev/docs/llms-full.txt

Use this snippet for a standard Playwright integration. It automatically installs Playwright and its dependencies.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { playwright } from "@trigger.dev/build/extensions/playwright";

export default defineConfig({
  project: "<project ref>",
  // Your other config settings...
  build: {
    extensions: [
      playwright(),
    ],
  },
});
```

--------------------------------

### Display help information

Source: https://trigger.dev/docs/llms-full.txt

Show the help information for the deploy command.

```bash
npx trigger.dev@latest deploy --help | -h
```

--------------------------------

### Prisma Config File Setup (Legacy Mode)

Source: https://trigger.dev/docs/llms-full.txt

This example uses a `prisma.config.ts` file to centralize Prisma configuration, simplifying the Trigger.dev setup for legacy mode. Ensure `dotenv/config` is imported if using environment variables.

```typescript
import { defineConfig, env } from "prisma/config";
import "dotenv/config";

export default defineConfig({
  schema: "prisma/schema.prisma",
  migrations: {
    path: "prisma/migrations",
  },
  datasource: {
    url: env("DATABASE_URL"),
    directUrl: env("DATABASE_URL_UNPOPOOLED"),
  },
});
```

```prisma
generator client {
  provider        = "prisma-client-js"
  previewFeatures = ["typedSql"]
}

datasource db {
  provider  = "postgresql"
  url       = env("DATABASE_URL")
  directUrl = env("DATABASE_URL_UNPOOLED")
}

model User {
  id        String  @id @default(cuid())
  email     String  @unique
  name      String?
}
```

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { prismaExtension } from "@trigger.dev/build/extensions/prisma";

export default defineConfig({
  project: process.env.TRIGGER_PROJECT_REF!,
  build: {
    extensions: [
      prismaExtension({
        mode: "legacy",
        configFile: "./prisma.config.ts", // Load from config file
        migrate: true,
        typedSql: true,
        // schema and migrations path are extracted from prisma.config.ts
      }),
    ],
  },
});
```

```typescript
import { PrismaClient } from "@prisma/client";
export * as sql from "@prisma/client/sql";

export const db = new PrismaClient({
  datasources: {
    db: {
      url: process.env.DATABASE_URL,
    },
  },
});
```

--------------------------------

### Install Trigger.dev SDK and Build Packages (bun)

Source: https://trigger.dev/docs/manual-setup

Install the necessary Trigger.dev SDK and build packages using bun.

```bash
bun add @trigger.dev/sdk@latest
bun add -D @trigger.dev/build@latest
```

--------------------------------

### Calling Fetch Endpoints for Token Minting and Session Start

Source: https://trigger.dev/docs/ai-chat/frontend

Configure `useTriggerChatTransport` to use REST endpoints for minting access tokens and starting chat sessions. This example shows how to type the fetch handlers using `AccessTokenParams` and `StartSessionParams` from `@trigger.dev/sdk/chat`.

```ts
import type { AccessTokenParams, StartSessionParams } from "@trigger.dev/sdk/chat";

const transport = useTriggerChatTransport({
  task: "my-chat",
  accessToken: async ({ chatId }: AccessTokenParams) => {
    const res = await fetch(`/api/chat/${chatId}/access-token`, { method: "POST" });
    return res.text();
  },
  startSession: async ({ chatId, taskId, clientData }: StartSessionParams) => {
    const res = await fetch(`/api/chat/${chatId}/start`, {
      method: "POST",
      body: JSON.stringify({ taskId, clientData }),
    });
    return res.json(); // { publicAccessToken: string }
  },
});
```

--------------------------------

### Install and run Trigger.dev CLI

Source: https://trigger.dev/docs/migration-mergent

Install the Trigger.dev CLI and run the local development server to set up a local environment that mirrors production.

```bash
npx trigger.dev@latest init
npx trigger.dev@latest dev
```

--------------------------------

### Initialize Supabase Project

Source: https://trigger.dev/docs/guides/frameworks/supabase-edge-functions-basic

Use this command to create a new Supabase project. Ensure you answer 'y' to generate VS Code settings for Deno and install recommended extensions if using VS Code.

```bash
supabase init
```

--------------------------------

### Configure Puppeteer Extension

Source: https://trigger.dev/docs/guides/examples/puppeteer

Add the Puppeteer extension to your trigger.config.ts to enable its use in your project. This is a necessary setup step for all Puppeteer examples.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { puppeteer } from "@trigger.dev/build/extensions/puppeteer";

export default defineConfig({
  project: "<project ref>",
  // Your other config settings...
  build: {
    // This is required to use the Puppeteer library
    extensions: [puppeteer()],
  },
});
```

--------------------------------

### String Manipulation Examples

Source: https://trigger.dev/docs/llms-full.txt

Shows common string operations including converting case, concatenating, extracting substrings, and getting string length.

```sql
SELECT
  lower(status) AS status_lower,
  upper(status) AS status_upper,
  concat(task_identifier, '-', status) AS combined,
  substring(run_id, 1, 8) AS short_id,
  length(task_identifier) AS name_length
FROM runs
```

--------------------------------

### Combined Delay and TTL Example

Source: https://trigger.dev/docs/triggering

Illustrates the timeline when both delay and TTL are used. TTL starts counting from the enqueue time, not the trigger time.

```typescript
await myTask.trigger({ some: "data" }, { delay: "10m", ttl: "1h" });

```

--------------------------------

### Install Dev Dependencies for Testing

Source: https://trigger.dev/docs/ai-chat/testing

Install Vitest, AI SDK, and provider packages using pnpm. The AI SDK provider is optional and only needed for specific type casting.

```bash
pnpm add -D vitest ai @ai-sdk/provider
```

--------------------------------

### Install AI SDK 7 Telemetry Adapter

Source: https://trigger.dev/docs/ai-chat/changelog

Install the `@ai-sdk/otel` adapter alongside `ai@7` to enable telemetry for model-call spans when using Vercel AI SDK 7. This ensures your `streamText` spans are recorded in the run trace without additional setup.

```sh
npm install @ai-sdk/otel
```

--------------------------------

### Inline Build Extension Example

Source: https://trigger.dev/docs/llms-full.txt

Defines a simple build extension inline within the `trigger.config.ts` file. This extension logs a message when the build starts.

```typescript
import { defineConfig } from "@trigger.dev/sdk";

export default defineConfig({
  project: "my-project",
  build: {
    extensions: [
      {
        name: "my-extension",
        onBuildStart: async (context) => {
          console.log("Build starting!");
        },
      },
    ],
  },
});
```

--------------------------------

### Deploy Command with Help Option

Source: https://trigger.dev/docs/cli-deploy-commands

Display help information for the deploy command using the --help or -h option.

```bash
npx trigger.dev@latest deploy --help
```

--------------------------------

### Configure Puppeteer Extension for Trigger.dev

Source: https://trigger.dev/docs/llms-full.txt

Add the Puppeteer extension to your trigger.config.ts to enable Puppeteer functionality in your project. This is a required setup step for all Puppeteer examples.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { puppeteer } from "@trigger.dev/build/extensions/puppeteer";

export default defineConfig({
  project: "<project ref>",
  // Your other config settings...
  build: {
    // This is required to use the Puppeteer library
    extensions: [puppeteer()],
  },
});
```

--------------------------------

### Show Help Information

Source: https://trigger.dev/docs/cli-preview-archive

Use the --help or -h option to display help information for the command.

```bash
npx trigger.dev@latest preview archive --help
```

--------------------------------

### Run Development Server with a Profile

Source: https://trigger.dev/docs/llms-full.txt

Execute the development server command using a previously configured profile.

```bash
npx trigger.dev@latest dev --profile self-hosted
```

--------------------------------

### Configure Lightpanda Extension with Options

Source: https://trigger.dev/docs/llms-full.txt

Customize the Lightpanda extension by specifying the version and disabling telemetry. This example shows how to install a 'nightly' version and disable telemetry.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { lightpanda } from "@trigger.dev/build/extensions/lightpanda";

export default defineConfig({
  project: "<project ref>",
  build: {
    extensions: [
      lightpanda({
        version: "nightly",
        disableTelemetry: true,
      }),
    ],
  },
});
```

--------------------------------

### Install Nango Frontend SDK

Source: https://trigger.dev/docs/guides/frameworks/nango

Install the Nango frontend SDK using npm. This is the first step to integrating Nango into your Next.js application.

```bash
npm install @nangohq/frontend
```

--------------------------------

### Basic Playwright Setup with Trigger.dev

Source: https://trigger.dev/docs/config/extensions/playwright

Use this basic configuration to include the Playwright build extension in your Trigger.dev project. It automatically installs Playwright and necessary browser dependencies.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { playwright } from "@trigger.dev/build/extensions/playwright";

export default defineConfig({
  project: "<project ref>",
  // Your other config settings...
  build: {
    extensions: [
      playwright(),
    ],
  },
});
```

--------------------------------

### Start Development Servers

Source: https://trigger.dev/docs/guides/frameworks/nango

Run your local development server and the Trigger.dev CLI. This allows for local testing and debugging of your tasks.

```bash
npm run dev
npx trigger.dev@latest dev

```

--------------------------------

### Add Prisma and OpenAI Instrumentations

Source: https://trigger.dev/docs/config/config-file

Configure your `trigger.config.ts` to include Prisma and OpenAI instrumentations. Ensure you have the necessary packages installed and follow any specific setup instructions for each instrumentation.

```typescript
import { defineConfig } from "@trigger.dev/sdk";
import { PrismaInstrumentation } from "@prisma/instrumentation";
import { OpenAIInstrumentation } from "@traceloop/instrumentation-openai";

export default defineConfig({
  project: "<project ref>",
  // Your other config settings...
  telemetry: {
    instrumentations: [new PrismaInstrumentation(), new OpenAIInstrumentation()],
  },
});
```

--------------------------------

### Start Development Environment

Source: https://trigger.dev/docs/guides/frameworks/sequin

Ensure all services are running before proceeding with the integration test. This includes the Next.js app, Trigger.dev dev server, and the Sequin tunnel.

```bash
npm run dev
```

```bash
npx trigger.dev@latest dev
```

```bash
sequin tunnel --ports=3001:local_endpoint
```

--------------------------------

### Using Typed Messages with `useChat`

Source: https://trigger.dev/docs/ai-chat/frontend

Pass the same message type through `useChat` when your chat agent is defined with `chat.withUIMessage` to narrow `messages` and `message.parts` on the client. This example demonstrates the setup with `useTriggerChatTransport` and `useChat`.

```tsx
import { useChat } from "@ai-sdk/react";
import { useTriggerChatTransport, type InferChatUIMessage } from "@trigger.dev/sdk/chat/react";
import type { myChat } from "./myChat";

type Msg = InferChatUIMessage<typeof myChat>;

const transport = useTriggerChatTransport<typeof myChat>({
  task: "my-chat",
  accessToken: ({ chatId }) => mintChatAccessToken(chatId),
  startSession: ({ chatId, clientData }) =>
      startChatSession({ chatId, clientData }),
});
const { messages } = useChat<Msg>({ transport });
```

--------------------------------

### Install Required Packages

Source: https://trigger.dev/docs/guides/frameworks/nango

Install the Nango and Anthropic SDKs using npm. These are necessary for authentication and AI summarization respectively.

```bash
npm install @nangohq/node @anthropic-ai/sdk
```

--------------------------------

### Configure Agent with exitAfterPreloadIdle

Source: https://trigger.dev/docs/ai-chat/lifecycle-hooks

Set `exitAfterPreloadIdle` to `true` for 'fire and forget' preloads. The run completes after the idle timeout if no user message is received. This example shows eager state setup in `onPreload`.

```typescript
export const myChat = chat.agent({
  id: "my-chat",
  preloadIdleTimeoutInSeconds: 10,
  exitAfterPreloadIdle: true,
  onPreload: async ({ chatId, clientData }) => {
    // Eagerly set up state. If no message comes, the run just ends.
    await initializeChat(chatId, clientData);
  },
  run: async ({ messages, signal }) => {
    return streamText({ model: anthropic("claude-sonnet-4-5"), messages, abortSignal: signal });
  },
});
```

--------------------------------

### Successful Deployment Output

Source: https://trigger.dev/docs/deployment/overview

Example output indicating a successful deployment of a new version with detected tasks.

```bash
Trigger.dev (3.3.16)
------------------------------------------------------
┌  Deploying project
│
◇  Retrieved your account details for eric@trigger.dev
│
◇  Successfully built code
│
◇  Successfully deployed version 20250228.1
│
└  Version 20250228.1 deployed with 4 detected tasks
```

--------------------------------

### useRealtimeStream Hook Options

Source: https://trigger.dev/docs/tasks/streams

This example illustrates the various options available when using the `useRealtimeStream` hook, including access token, custom API URL, timeout, start index, throttling, and data callbacks.

```tsx
const { parts, error } = useRealtimeStream(streamDef, runId, {
  accessToken: "pk_...", // Required: Public access token
  baseURL: "https://api.trigger.dev", // Optional: Custom API URL
  timeoutInSeconds: 60, // Optional: Timeout (default: 60)
  startIndex: 0, // Optional: Start from specific chunk
  throttleInMs: 16, // Optional: Throttle updates (default: 16ms)
  onData: (chunk) => {}, // Optional: Callback for each chunk
});
```

--------------------------------

### Deploy Command with Environment Option

Source: https://trigger.dev/docs/cli-deploy-commands

Use the --env or -e option to specify the deployment environment (e.g., staging, preview). Defaults to 'prod'.

```bash
npx trigger.dev@latest deploy --env staging
```

--------------------------------

### Example chat.headStart Handler Configuration

Source: https://trigger.dev/docs/ai-chat/fast-starts

An example of how to configure and export a `chat.headStart` handler. This snippet shows setting a specific agent ID and trigger configuration, including tags and machine type, and defines the `run` callback to stream text with specified model and system prompts.

```typescript
export const chatHandler = chat.headStart({
  agentId: "my-chat",
  triggerConfig: { tags: ["org:acme"], queue: "chat", machine: "small-2x" },
  run: async ({ chat: helper }) =>
    streamText({ ...helper.toStreamTextOptions({ tools: headStartTools }), model, system }),
});
```

--------------------------------

### Accessing Task Context in TypeScript

Source: https://trigger.dev/docs/context

Use the `ctx` object passed to the `run` function to access task context. The context is fixed at the start of the run and does not change during execution. This example checks the environment type.

```typescript
import {
  task
} from "@trigger.dev/sdk";

export const parentTask = task({
  id: "parent-task",
  run: async (payload: { message: string }, { ctx }) => {
    if (ctx.environment.type === "DEVELOPMENT") {
      return;
    }
  },
});
```

--------------------------------

### Example Payload for Real-time Image Generation Task

Source: https://trigger.dev/docs/llms-full.txt

This JSON object demonstrates the expected payload structure for the `realtimeImageGeneration` task. It includes a URL to an image and a text prompt to guide the image generation process.

```json
{
  "imageUrl": "https://static.vecteezy.com/system/resources/previews/005/857/332/non_2x/funny-portrait-of-cute-corgi-dog-outdoors-free-photo.jpg",
  "prompt": "Dress this dog for Christmas"
}
```

--------------------------------

### SKILL.md Frontmatter Example

Source: https://trigger.dev/docs/ai-chat/patterns/skills

Shows the required frontmatter for a SKILL.md file, including the skill's name and a description for the agent.

```yaml
---
name: time-utils
description: Compute and format dates/times in arbitrary timezones. Use when the user asks "what time is it", timezone conversions, or date math.
---
```

--------------------------------

### Run Next.js Development Server

Source: https://trigger.dev/docs/guides/frameworks/nextjs-webhooks

Commands to start the Next.js development server using npm, pnpm, or yarn.

```bash
npm run dev
```

```bash
pnpm run dev
```

```bash
yarn dev
```