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://mp-staging.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/langgraph.md

Temporal LangGraph Plugin (Python)

Overview

The LangGraphPlugin runs LangGraph nodes and tasks as Temporal Activities, giving LangGraph-orchestrated AI workflows durable execution, automatic retries, and timeouts.

Both LangGraph APIs are supported:

  • Graph API (StateGraph).

  • Functional API (@entrypoint / @task).

The plugin ships in the Temporal Python SDK at temporalio.contrib.langgraph.

[!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 general Temporal Python AI/LLM patterns (Pydantic data converter, LLM Activity design, retry classification, multi-agent orchestration), read references/python/ai-patterns.md first; for language-agnostic patterns, read references/core/ai-patterns.md.

Installation

uv add temporalio[langgraph]

This pulls in langgraph as well for you.

Public API

temporalio.contrib.langgraph exports four symbols:

  • LangGraphPlugin — the plugin class. Pass to both the Client and the Worker.

  • graph(name, cache=...) — Workflow-side accessor that returns a registered StateGraph by name.

  • entrypoint(name, cache=...) — Workflow-side accessor that returns a registered Functional-API Pregel.

  • cache() — accessor for the per-workflow LangGraph cache.

Build the plugin

Construct the plugin once at startup. The constructor signature is:

LangGraphPlugin(
    graphs: dict[str, StateGraph] | None = None,
    entrypoints: dict[str, Pregel] | None = None,
    tasks: list | None = None,
    activity_options: dict[str, dict[str, Any]] | None = None,
    default_activity_options: dict[str, Any] | None = None,
)
Graph API

Register your StateGraph instances in graphs=, keyed by a name your workflow code will look up with graph(name):

from langgraph.graph import StateGraph
from temporalio.contrib.langgraph import LangGraphPlugin

g = StateGraph(State)
g.add_node("my_node", my_node, metadata={"execute_in": "activity"})

plugin = LangGraphPlugin(graphs={"my-graph": g})
Functional API

Pass entrypoints in entrypoints=, tasks in tasks=, and per-task activity options in activity_options= (keyed by task function name):

from temporalio.contrib.langgraph import LangGraphPlugin

plugin = LangGraphPlugin(
    entrypoints={"my_entrypoint": my_entrypoint},
    tasks=[my_task],
    activity_options={"my_task": {"execute_in": "activity"}},
)

Register the plugin on Client and Worker

Pass the same LangGraphPlugin instance to both the Temporal Client and the Worker via their plugins= parameter, like any other Temporal Python SDK plugin:

from temporalio.client import Client
from temporalio.worker import Worker

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

worker = Worker(
    client,
    task_queue="my-task-queue",
    workflows=[MyWorkflow],
    plugins=[plugin],
)
await worker.run()

Execution location — required per node and per task

Every node (Graph API) and every task (Functional API) must declare execute_in, set to either "activity" or "workflow":

# Graph API — set via node metadata
graph.add_node("my_node", my_node, metadata={"execute_in": "activity"})
graph.add_node("tool_node", tool_node, metadata={"execute_in": "workflow"})

# Functional API — set via activity_options on the plugin
plugin = LangGraphPlugin(
    tasks=[my_task, tool_task],
    activity_options={
        "my_task": {"execute_in": "activity"},
        "tool_task": {"execute_in": "workflow"},
    },
)

  • Use "activity" for I/O, LLM calls, or anything that needs Temporal retries and timeouts.

  • Use "workflow" for logic that should run on the workflow thread: purely deterministic logic, or logic which orchestrates Temporal durable primitives within the workflow thread (e.g. multiple activity calls, wait conditions, etc.)

  • execute_in cannot be defaulted in default_activity_options — it must be specified individually per node or task.

Activity options

For nodes or tasks with execute_in: "activity", you can pass parameters that flow through to workflow.execute_activity(): start_to_close_timeout, retry_policy, schedule_to_close_timeout, heartbeat_timeout.

Graph API — options in node metadata
from datetime import timedelta
from temporalio.common import RetryPolicy

g = StateGraph(State)
g.add_node("my_node", my_node, metadata={
    "execute_in": "activity",
    "start_to_close_timeout": timedelta(seconds=30),
    "retry_policy": RetryPolicy(maximum_attempts=3),
})
Functional API — options keyed by task name
from datetime import timedelta
from temporalio.common import RetryPolicy
from temporalio.contrib.langgraph import LangGraphPlugin

plugin = LangGraphPlugin(
    entrypoints={"my_entrypoint": my_entrypoint},
    tasks=[my_task],
    activity_options={
        "my_task": {
            "execute_in": "activity",
            "start_to_close_timeout": timedelta(seconds=30),
            "retry_policy": RetryPolicy(maximum_attempts=3),
        },
    },
)

Run a graph from a Workflow

Inside the Workflow, get the registered graph by name with graph(name), compile it, then ainvoke (or astream) as usual. If the graph requires a checkpointer (for example, when using interrupts), use InMemorySaver — Temporal supplies durability, so third-party checkpointers like PostgreSQL or Redis are not needed:

import typing
import langgraph.checkpoint.memory
from temporalio import workflow
from temporalio.contrib.langgraph import graph

@workflow.defn
class MyWorkflow:
    @workflow.run
    async def run(self, input: str) -> typing.Any:
        g = graph("my-graph").compile(
            checkpointer=langgraph.checkpoint.memory.InMemorySaver(),
        )
        return await g.ainvoke({"input": input})

Use entrypoint(name) instead of graph(name) for Functional-API entrypoints.

Runtime context

LangGraph's run-scoped context (context_schema) is reconstructed on the Activity side, so a node can read and write runtime.context even when the node runs as an Activity:

from langgraph.runtime import Runtime
from typing_extensions import TypedDict
from temporalio.contrib.langgraph import graph

class Context(TypedDict):
    user_id: str

async def my_node(state: State, runtime: Runtime[Context]) -> dict:
    return {"user": runtime.context["user_id"]}

# In the Workflow:
g = graph("my-graph").compile()
await g.ainvoke({...}, context=Context(user_id="alice"))

The context object must be serializable by the configured Temporal payload converter, since it crosses the Activity boundary. If your context uses Pydantic models, configure pydantic_data_converter — see references/python/ai-patterns.md.

Tracing

For LangSmith tracing of LangGraph nodes and Temporal Activities together, use the Temporal LangSmith plugin (references/python/integrations/langsmith.md).

Hard constraints

  • execute_in is mandatory on every node and task. Set it to "activity" or "workflow" per node/task — it cannot be set in default_activity_options.

  • Use InMemorySaver as your checkpointer. Temporal handles durability; do not configure PostgreSQL, Redis, or other third-party checkpointers.

  • LangGraph Store is not supported across the Activity boundary. If you pass a Store (e.g. InMemoryStore via graph.compile(store=...) or @entrypoint(store=...)), the plugin logs a warning on first use and runtime.store is None inside nodes. Use Workflow state for per-run memory, or an external database (Postgres/Redis/etc.) configured on each worker for shared memory across runs.

  • Context objects must be serializable by the configured Temporal payload converter, since they cross the Activity boundary.

Resources

  • references/python/ai-patterns.md — Python AI/LLM patterns (Pydantic data converter, LLM Activity design, retry/error classification).

  • references/core/ai-patterns.md — language-agnostic AI/LLM patterns.

  • references/python/integrations/langsmith.md - Companion LangSmith plugin.

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