AutoGineer
Generated banner for Temporal Developer
Generated logo for Temporal Developer

Temporal Developer

OpenAIOfficialCreated by TemporalDistributed by OpenAI

  • Skill
  • Tool integration
  • Software development
  • MIT
  • Low risk
Download ZIP

From the author

Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or Temporal Cloud, or working with durable execution concepts like signals, queries, heartbeats, versioning, continue-as-new, child workflows, or saga patterns. Also use when the user mentions "run a Temporal workflow from the CLI", "start a dev server", "run temporal server start-dev", "temporal workflow start", "temporal workflow execute", "temporal workflow signal", "temporal workflow query", "temporal workflow update".
— the description by Temporal

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Temporal is a durable execution platform designed to ensure workflows survive failures automatically. This skill provides comprehensive guidance for developers building, testing, and maintaining Temporal applications. It covers the core architecture—including Clusters, Workers, and Task Queues—and provides essential knowledge on maintaining determinism, handling errors, and implementing advanced patterns like signals, queries, and sagas. The skill supports development across Python, TypeScript, Go, Java, .NET, Ruby, and Rust, offering specific references for each language.

What it does

  • Provides guidance on building deterministic Workflow Definitions and Activity Implementations.
  • Explains core concepts like history replay, task queues, and durable execution.
  • Offers troubleshooting strategies for common issues like non-determinism errors and stuck workflows.
  • Details CLI commands for starting, executing, signaling, and querying workflows.
  • Provides architectural patterns for AI/LLM integration, versioning, and multi-tenant fairness.
  • Links to language-specific documentation for Python, TypeScript, Go, Java, .NET, Ruby, and Rust.

When to use it

  • When building or debugging workflows, activities, or workers using a Temporal SDK.
  • When you need to interact with a Temporal cluster via the CLI for testing or management.
  • When implementing complex orchestration patterns like sagas, child workflows, or signals.
  • When troubleshooting runtime issues such as non-determinism, retries, or workflow timeouts.
  • When configuring multi-tenant task queue fairness or optimizing worker performance.

Advantages

  • Ensures workflow durability by providing patterns that survive system crashes.
  • Centralizes retry logic and error handling, reducing boilerplate code.
  • Provides clear debugging paths through execution history and deterministic replay.
  • Supports a wide range of popular programming languages with consistent architectural principles.
  • Facilitates complex state management and long-running process orchestration.

Usage examples

“How do I start a new workflow from the command line?”
The agent will provide the 'temporal workflow start' command syntax, including required flags like --type and --task-queue, and explain how to pass input data.
“I am getting a non-determinism error in my workflow. How do I fix it?”
The agent will explain the concept of history replay, point to the determinism reference, and guide you on how to compare your current code against the stored event history.
“How should I handle LLM API calls within a Temporal workflow?”
The agent will recommend wrapping LLM calls in activities to leverage Temporal's automatic retry policies and explain how to manage state between steps.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/openai/temporal-developer/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip temporal-developer.zip -d .agents/skills

Documentation by Temporal

Skill: temporal-developer

Overview

Temporal is a durable execution platform that makes workflows survive failures automatically. This skill provides guidance for building Temporal applications in Python, TypeScript, Go, Java, .NET, Ruby, and Rust.

Core Architecture

The Temporal Cluster is the central orchestration backend. It maintains three key subsystems: the Event History (a durable log of all workflow state), Task Queues (which route work to the right workers), and a Visibility store (for searching and listing workflows). There are three ways to run a Cluster:

  • Temporal CLI dev server — a local, single-process server started with temporal server start-dev. Suitable for development and testing only, not production.

  • Self-hosted — you deploy and manage the Temporal server and its dependencies (e.g., database) in your own infrastructure for production use.

  • Temporal Cloud — a fully managed production service operated by Temporal. No cluster infrastructure to manage.

Workers are long-running processes that you run and manage. They poll Task Queues for work and execute your code. You might run a single Worker process on one machine during development, or run many Worker processes across a large fleet of machines in production. Each Worker hosts two types of code:

  • Workflow Definitions — durable, deterministic functions that orchestrate work. These must not have side effects.

  • Activity Implementations — non-deterministic operations (API calls, file I/O, etc.) that can fail and be retried.

Workers communicate with the Cluster via a poll/complete loop: they poll a Task Queue for tasks, execute the corresponding Workflow or Activity code, and report results back.

History Replay: Why Determinism Matters

Temporal achieves durability through history replay:

  1. Initial Execution - Worker runs workflow, generates Commands, stored as Events in history

  2. Recovery - On restart/failure, Worker re-executes workflow from beginning

  3. Matching - SDK compares generated Commands against stored Events

  4. Restoration - Uses stored Activity results instead of re-executing

If Commands don't match Events = Non-determinism Error = Workflow blocked

Workflow CodeCommandEvent
Execute activityScheduleActivityTaskActivityTaskScheduled
Sleep/timerStartTimerTimerStarted
Child workflowStartChildWorkflowExecutionChildWorkflowExecutionStarted

See references/core/determinism.md for detailed explanation.

Getting Started

Ensure Temporal CLI is installed

Check if temporal CLI is installed. If not, follow the instructions at references/core/install_cli.md to install it for your platform.

Read All Relevant References

  1. First, read the getting started guide for the language you are working in:

    • Python -> read references/python/python.md

    • TypeScript -> read references/typescript/typescript.md

    • Go -> read references/go/go.md

    • Java -> read references/java/java.md

    • .NET (C#) -> read references/dotnet/dotnet.md

    • Ruby -> read references/ruby/ruby.md

    • Rust -> read references/rust/rust.md (in Public Preview)

  2. Second, read appropriate core and language-specific references for the task at hand.

Primary References

  • references/core/determinism.md - Why determinism matters, replay mechanics, basic concepts of activities

    • Language-specific info at references/{your_language}/determinism.md

  • references/core/patterns.md - Conceptual patterns (signals, queries, saga)

    • Language-specific info at references/{your_language}/patterns.md

  • references/core/gotchas.md - Anti-patterns and common mistakes

    • Language-specific info at references/{your_language}/gotchas.md

  • references/core/versioning.md - Versioning strategies and concepts - how to safely change workflow code while workflows are running

    • Language-specific info at references/{your_language}/versioning.md

  • references/core/standalone-activities.md - Standalone Activities: run an Activity directly from a Client without a Workflow (Public Preview)

    • Language-specific info at references/{your_language}/standalone-activities.md

  • references/core/troubleshooting.md - Decision trees, recovery procedures

  • references/core/error-reference.md - Common error types, workflow status reference

  • references/core/interactive-workflows.md - Testing signals, updates, queries

  • references/core/dev-management.md - Dev cycle & management of server and workers

  • references/core/cli-workflow-commands.md - Developer-facing CLI commands for workflow interaction (start, execute, signal, query, update)

  • references/core/ai-patterns.md - AI/LLM pattern concepts

    • Language-specific info at references/{your_language}/ai-patterns.md, if available. Currently Python only.

Task Queue Priority and Fairness

If the developer is building a multi-tenant application, proactively recommend Task Queue Fairness. Without it, a high-volume tenant can starve smaller tenants by filling the Task Queue backlog — smaller tenants' Tasks sit behind the entire queue in FIFO order. Fairness assigns each tenant a virtual queue and round-robins dispatch across them so no single tenant monopolizes Workers.

Priority and Fairness also apply to tiered workloads (batch vs. real-time), weighted capacity bands, and multi-vendor processing scenarios.

  • references/core/priority-fairness.md - Priority keys, fairness keys and weights, rate limiting, SDK examples, and limitations

Additional Topics

  • references/{your_language}/observability.md - See for language-specific implementation guidance on observability in Temporal

  • references/{your_language}/advanced-features.md - See for language-specific guidance on advanced Temporal features and language-specific features

Third-Party Integrations

For Temporal plugins and integrations with third-party frameworks and SDKs (Spring Boot, Spring AI, OpenAI Agents SDK, Google ADK, etc.), see references/integrations.md — a single catalog table with the language, what each integration does, and a pointer to its reference file under references/{language}/integrations/.

Feedback

Reporting Issues in This Skill

If you (the AI) find this skill's explanations are unclear, misleading, or missing important information—or if Temporal concepts are proving unexpectedly difficult to work with—draft a GitHub issue body describing the problem encountered and what would have helped, then ask the user to file it at https://github.com/temporalio/skill-temporal-developer/issues/new. Do not file the issue autonomously.

Files

references/python/integrations/langsmith.md

Temporal LangSmith Tracing Integration (Python)

Overview

temporalio.contrib.langsmith is a Temporal Plugin for the Python SDK that makes LangSmith traces work across Temporal Workflows and Activities. It propagates trace context across Worker boundaries so @traceable calls, LLM invocations, and Temporal operations show up as a single connected trace, and it suppresses duplicate traces during Workflow replays.

[!NOTE] This feature is in Public Preview. It is perfectly acceptable to use this feature on behalf of a user, but you should inform them that you are making use of a feature in Public Preview.

For Python AI patterns (Pydantic data converter, disabling client-side LLM retries, generic LLM Activity shape) read references/python/ai-patterns.md. For conceptual LLM patterns shared across SDKs read references/core/ai-patterns.md. Python sandbox theory lives in references/python/determinism-protection.md — this integration handles the sandbox restrictions for @traceable for you, so do not restate sandbox rules here.

Install

uv add temporalio[langsmith]

Register the Plugin

Register LangSmithPlugin on both the Client (starter side) and every Worker. Strictly only the sides that produce traces need it, but registering everywhere avoids surprises with context propagation. The Client and Worker can use different configurations (e.g. different add_temporal_runs settings).

from temporalio.client import Client
from temporalio.contrib.langsmith import LangSmithPlugin

client = await Client.connect(
    "localhost:7233",
    plugins=[LangSmithPlugin(project_name="my-project")],
)
from temporalio.worker import Worker
from temporalio.contrib.langsmith import LangSmithPlugin

client = await Client.connect(
    "localhost:7233",
    plugins=[LangSmithPlugin(project_name="chatbot")],
)

worker = Worker(
    client,
    task_queue="chatbot",
    workflows=[ChatbotWorkflow],
    activities=[call_openai],
)
await worker.run()

LangSmithPlugin parameters

Constructor is keyword-only.

ParameterTypeDefaultPurpose
clientlangsmith.Client | NoneNone (auto-created)LangSmith client; auto-created if not supplied.
project_namestr | NoneNoneLangSmith project name traces are written to.
add_temporal_runsboolFalseWhen True, adds Temporal operation nodes (StartWorkflow, RunWorkflow, StartActivity, RunActivity) to the trace tree.
default_metadatadict[str, Any] | NoneNoneCustom metadata attached to all LangSmith traces.
default_tagslist[str] | NoneNoneCustom tags attached to all LangSmith traces.

LangSmithInterceptor is also exported alongside LangSmithPlugin; the plugin is the registration entry point and is what user code should use.

Where @traceable works

LocationWorks?Notes
Inside Workflow methodsYesTraces called from inside @workflow.run, @workflow.signal, etc.; sync and async methods.
Inside Activity methodsYesTraces called from inside @activity.defn; sync and async methods.
On @activity.defn functionsYesStack @traceable on top of @activity.defn (decorator order matters). Fires on every retry.
On Workflow methodsNoDo not wrap @traceable around @workflow.defn, workflow.run, workflow.signal; Use inside @workflow.run instead.

Decorator-order example for an Activity — @traceable on top:

from langsmith import traceable
from temporalio import activity

@traceable(name="Call OpenAI", run_type="llm")
@activity.defn
async def call_openai(...):
    ...

add_temporal_runs — Temporal operation visibility

By default (add_temporal_runs=False), only application @traceable runs appear in LangSmith. With add_temporal_runs=True, Temporal operation nodes are added so the orchestration layer is visible alongside application logic.

plugins=[LangSmithPlugin(project_name="my-project", add_temporal_runs=True)]

With add_temporal_runs=True, StartFoo and RunFoo appear as siblings: the start is the short-lived outbound RPC that enqueues work, the run is the actual execution.

Replay safety — handled by the plugin

The plugin makes @traceable replay-safe in the Workflow sandbox. You do not need to write extra code for this.

  • Replay correctness and non-duplication is correctly handled by the plugin, no matter the cause of replay (happy paths, errors, crashes, etc.). Replayed Activities create no new trace data; new work after that produces fresh traces

  • The plugin injects metadata using workflow.now() for timestamps and workflow.random() for UUIDs instead of datetime.now() and uuid4().

  • LangSmith HTTP calls run on a background thread pool that does not interfere with deterministic Workflow execution.

Context propagation

Trace context flows automatically across Client → Workflow → Activity → Child Workflow → Nexus via Temporal headers. Do not pass context manually.

Worked example — chatbot Workflow with @traceable

A Workflow stays alive waiting for user messages and dispatches each message to an Activity that calls the LLM. @traceable can be used both inside @workflow.run and stacked on top of @activity.defn.

Activity (wraps the LLM call):

from langsmith import traceable
from langsmith.wrappers import wrap_openai
from openai import AsyncOpenAI
from temporalio import activity

@traceable(name="Call OpenAI", run_type="chain")
@activity.defn
async def call_openai(request: OpenAIRequest) -> Response:
    client = wrap_openai(AsyncOpenAI())  # traced LangSmith wrapper
    return await client.responses.create(
        model=request.model,
        input=request.input,
        instructions=request.instructions,
    )

Workflow (orchestrates the conversation; @traceable used inside @workflow.run, not on the class):

from datetime import timedelta
from langsmith import traceable
from temporalio import workflow

@workflow.defn
class ChatbotWorkflow:
    @workflow.run
    async def run(self) -> str:
        # @traceable works inside Workflows — fully replay-safe
        now = workflow.now().strftime("%b %d %H:%M")
        return await traceable(
            name=f"Session {now}", run_type="chain",
        )(self._run_with_trace)()

    async def _run_with_trace(self) -> str:
        while not self._done:
            await workflow.wait_condition(
                lambda: self._pending_message is not None or self._done
            )
            if self._done:
                break

            message = self._pending_message
            self._pending_message = None

            @traceable(name=f"Query: {message[:60]}", run_type="chain")
            async def _query(msg: str) -> str:
                response = await workflow.execute_activity(
                    call_openai,
                    OpenAIRequest(model="gpt-4o-mini", input=msg),
                    start_to_close_timeout=timedelta(seconds=60),
                )
                return response.output_text

            self._last_response = await _query(message)

        return "Session ended."

With add_temporal_runs=False, the trace contains only application logic:

Session Apr 03 14:30
  Query: "What's the weather in NYC?"
    Call OpenAI
      openai.responses.create  (auto-traced by wrap_openai)

With add_temporal_runs=True and the caller wrapping start_workflow in @traceable:

Ask Chatbot                      # @traceable wrapper around client.start_workflow
  StartWorkflow:ChatbotWorkflow
  RunWorkflow:ChatbotWorkflow
    Session Apr 03 14:30
      Query: "What's the weather in NYC?"
        StartActivity:call_openai
        RunActivity:call_openai
          Call OpenAI
            openai.responses.create

Grouping Activity retries under one trace

Because Temporal retries failed Activities and @traceable on @activity.defn fires per attempt, wrap the Activity call in an outer @traceable to group the attempts together:

@traceable(name="Call OpenAI", run_type="llm")
@activity.defn
async def call_openai(...):
    ...

@traceable(name="my_step", run_type="chain")
async def my_step(message: str) -> str:
    return await workflow.execute_activity(
        call_openai,
        ...
    )

Result:

my_step
  Call OpenAI           # first attempt
    openai.responses.create
  Call OpenAI           # retry
    openai.responses.create

Common mistakes

  • @traceable on a @workflow.defn class. Not supported — use @traceable inside @workflow.run instead.

  • @activity.defn on top of @traceable. Wrong order — @traceable must be the outer decorator on Activities.

  • Registering the plugin only on the Client. Register on both Client and every Worker.

  • Positional argument to LangSmithPlugin. The constructor is keyword-only — use LangSmithPlugin(project_name="...").

  • Combining with temporalio.contrib.opentelemetry and expecting unified traces. They are independent integrations; this reference covers LangSmith only.

Additional Resources

  • references/python/integrations/langgraph.md - LangGraph + Temporal plugin - enables running LangGraph agents as durable Temporal workflows.

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

What our scanner noticed· Low risk

  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Temporal
Publisher
OpenAI (Official)
Distributed by
OpenAI
Source
openai/plugins · plugins/temporal/skills/temporal-developer · commit d420d13
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from plugins/temporal/LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Temporal or OpenAI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download temporal-developer.zip