Dust Temporal logo

Dust Temporal

OrganizationPopular
dust-tt
dust-temporal

Step-by-step guide for creating Temporal workflows in Dust. Use when adding background jobs, async processing, durable workflows, or task queues.

Overview

Publisherdust-tt
Repositorydust
Skill namedust-temporal
Stars
1.5K
Forks
370
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dust-tt on GitHub. Read the source before you install it.

Installation

Install the Dust Temporal AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dust-tt/dust/tree/main/.claude/skills/dust-temporal
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dust-tt/dust.git /tmp/dust
mkdir -p .claude/skills
cp -r /tmp/dust/.claude/skills/dust-temporal .claude/skills/dust-temporal
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dust Temporal in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dust Temporal on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dust Temporal is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Creating Temporal Workflows

This skill guides you through creating Temporal workflows for durable background processing.

Quick Reference

Files Structure (per queue)

temporal/your_queue/
├── config.ts          # Queue name and version
├── helpers.ts         # Workflow ID generators
├── activities.ts      # Activity implementations (DB, API calls)
├── workflows.ts       # Workflow orchestration
├── worker.ts          # Worker setup
└── client.ts          # Workflow launcher functions

Key Concepts

  • Workflow: Durable, deterministic function that orchestrates activities
  • Activity: Non-deterministic function with side effects (DB, API calls)
  • Task Queue: Named queue where workflows/activities execute
  • Workflow ID: Unique identifier for idempotency

Step-by-Step Implementation

Step 1: Create Queue Configuration

Create temporal/your_queue/config.ts:

typescript
const QUEUE_VERSION = 1;
export const QUEUE_NAME = `your-queue-v${QUEUE_VERSION}`;

Step 2: Create Workflow ID Helper

Create temporal/your_queue/helpers.ts:

typescript
export function makeYourWorkflowId({ entityId }: { entityId: string }): string {
  return `your-workflow-${entityId}`;
}

Important: Workflow IDs must be deterministic (same inputs = same ID) for idempotency.

Step 3: Create Activities

Create temporal/your_queue/activities.ts:

typescript
import { YourResource } from "@app/lib/resources/your_resource";
import logger from "@app/logger/logger";

export async function yourActivity({
  entityId,
  workspaceId,
}: {
  entityId: string;
  workspaceId: number;
}): Promise<void> {
  const entity = await YourResource.fetchById(entityId);
  if (!entity) {
    throw new Error(`Entity not found: ${entityId}`);
  }

  const result = await entity.doSomething();
  if (result.isErr()) {
    logger.error({ entityId, error: result.error }, "Failed to process entity");
    throw new Error(`Failed to process: ${result.error.message}`);
  }
}

Guidelines: Activities perform side effects, can throw (Temporal retries), should be idempotent.

Step 4: Create Workflow

Create temporal/your_queue/workflows.ts:

typescript
import { proxyActivities } from "@temporalio/workflow";
import type * as activities from "@app/temporal/your_queue/activities";

const { yourActivity } = proxyActivities<typeof activities>({
  startToCloseTimeout: "5 minutes",
});

export async function yourWorkflow({
  entityId,
  workspaceId,
}: {
  entityId: string;
  workspaceId: number;
}): Promise<void> {
  await yourActivity({ entityId, workspaceId });
}

Guidelines: Workflows are deterministic - no Math.random(), Date.now(), etc.

Step 5: Create Client Launcher

Create temporal/your_queue/client.ts:

typescript
import { WorkflowExecutionAlreadyStartedError } from "@temporalio/client";
import { getTemporalClientForFrontNamespace } from "@app/lib/temporal";
import logger from "@app/logger/logger";
import { QUEUE_NAME } from "@app/temporal/your_queue/config";
import { makeYourWorkflowId } from "@app/temporal/your_queue/helpers";
import { yourWorkflow } from "@app/temporal/your_queue/workflows";
import type { Result } from "@app/types";
import { Err, normalizeError, Ok } from "@app/types";

export async function launchYourWorkflow({
  entityId,
  workspaceId,
}: {
  entityId: string;
  workspaceId: number;
}): Promise<Result<undefined, Error>> {
  const client = await getTemporalClientForFrontNamespace();
  const workflowId = makeYourWorkflowId({ entityId });

  try {
    await client.workflow.start(yourWorkflow, {
      args: [{ entityId, workspaceId }],
      taskQueue: QUEUE_NAME,
      workflowId,
      memo: { entityId, workspaceId },
    });
    return new Ok(undefined);
  } catch (e) {
    if (!(e instanceof WorkflowExecutionAlreadyStartedError)) {
      logger.error({ workflowId, entityId, workspaceId, error: e }, "Failed starting workflow");
    }
    return new Err(normalizeError(e));
  }
}

Step 6: Create Worker

Create temporal/your_queue/worker.ts:

typescript
import type { Context } from "@temporalio/activity";
import { Worker } from "@temporalio/worker";
import { getTemporalWorkerConnection, TEMPORAL_MAXED_CACHED_WORKFLOWS } from "@app/lib/temporal";
import { ActivityInboundLogInterceptor } from "@app/lib/temporal_monitoring";
import logger from "@app/logger/logger";
import * as activities from "@app/temporal/your_queue/activities";
import { getWorkflowConfig } from "@app/temporal/bundle_helper";
import { QUEUE_NAME } from "./config";

export async function runYourQueueWorker() {
  const { connection, namespace } = await getTemporalWorkerConnection();

  const worker = await Worker.create({
    ...getWorkflowConfig({
      workerName: "your_queue",
      getWorkflowsPath: () => require.resolve("./workflows"),
    }),
    activities,
    taskQueue: QUEUE_NAME,
    maxCachedWorkflows: TEMPORAL_MAXED_CACHED_WORKFLOWS,
    maxConcurrentActivityTaskExecutions: 16,
    connection,
    namespace,
    interceptors: {
      activityInbound: [(ctx: Context) => new ActivityInboundLogInterceptor(ctx, logger)],
    },
  });

  await worker.run();
}

Step 7: Register Worker (Critical!)

Edit temporal/worker_registry.ts:

typescript
// 1. Add import
import { runYourQueueWorker } from "@app/temporal/your_queue/worker";

// 2. Add to WorkerName type
export type WorkerName =
  | "agent_loop_interactive"
  // ... existing workers
  | "your_queue"; // <- Add this

// 3. Add to workerFunctions mapping
export const workerFunctions: Record<WorkerName, () => Promise<void>> = {
  // ... existing workers
  your_queue: runYourQueueWorker, // <- Add this
};

Without registration, workflows will never execute!

Timeout & Retry Configuration

typescript
const { yourActivity } = proxyActivities<typeof activities>({
  startToCloseTimeout: "5 minutes",
  retry: {
    maximumAttempts: 3,
    initialInterval: "1s",
    backoffCoefficient: 2,
    maximumInterval: "1m",
    nonRetryableErrorTypes: ["ValidationError"],
  },
});

Validation Checklist

  • Queue config created with versioned name
  • Workflow ID helper is deterministic
  • Activities handle errors properly
  • Workflow uses proxyActivities with appropriate timeouts
  • Client returns Result<> and handles WorkflowExecutionAlreadyStartedError
  • Worker registered in worker_registry.ts
  • Tested locally

Reference Examples

See temporal/ directory for existing implementations.

Frequently asked questions

What does the Dust Temporal AI skill do?

Step-by-step guide for creating Temporal workflows in Dust. Use when adding background jobs, async processing, durable workflows, or task queues.

Why use Dust Temporal on TypingMind?

Because you install it once and use it with any model. Dust Temporal is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dust Temporal in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dust-tt/dust/tree/main/.claude/skills/dust-temporal. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dust Temporal?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dust Temporal?

As many as you like. As long as a model supports skills, you can use Dust Temporal with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dust Temporal AI skill free?

Yes. It is published on GitHub by dust-tt under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇