Upstash Workflow JS — Agent Skill by Upstash

From the author

Work with the @upstash/workflow TypeScript/JavaScript SDK for durable, long-running workflows in serverless functions, multi-step processes that survive timeouts, retries, and restarts (built on QStash). Use when defining a workflow endpoint with serve(), running steps with context.run, sleeping for minutes to days without holding a function open, calling external APIs with context.call, waiting for an external event or webhook, invoking other workflows, configuring retries, failure callbacks, and a DLQ, controlling concurrency, rate, and parallelism, triggering, cancelling, or inspecting runs with the Workflow client, building AI agents and orchestrators, human-in-the-loop approvals, realtime updates, local development with the QStash dev server, adding middleware, or migrating workflows safely. Also use when the user asks for durable execution, step functions, saga or orchestration patterns, background jobs with checkpoints, or long-running tasks on Vercel, Next.js, Cloudflare Workers, or other serverless

— the description by Upstash

AutoGineer summary

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

The Upstash Workflow SDK enables developers to create reliable, multi-step workflows within serverless environments. By leveraging QStash, it allows functions to survive timeouts, retries, and restarts, effectively managing long-running processes that span minutes or days without keeping the underlying function execution active. It supports complex orchestration patterns, including step-by-step execution, external API calls, event waiting, human-in-the-loop approvals, and sophisticated flow control.

What it does

Exposes serverless endpoints for durable workflow execution.
Manages multi-step processes that persist across function restarts and timeouts.
Provides tools for flow control, including concurrency, rate limiting, and parallelism.
Supports advanced patterns like cross-workflow invocation and waiting for external events.
Enables local development and testing via the QStash dev server.
Facilitates human-in-the-loop workflows and real-time updates.

When to use it

When building long-running tasks that exceed standard serverless function execution limits.
When implementing saga or orchestration patterns in a distributed system.
When you need reliable background jobs with built-in checkpointing and retries.
When building AI agents or orchestrators that require stateful, multi-step execution.
When integrating human approval steps into automated backend processes.

Advantages

Eliminates the need to hold serverless functions open for long durations.
Built-in support for retries, failure callbacks, and dead-letter queues.
Seamless integration with popular serverless platforms like Vercel and Cloudflare Workers.
Simplifies complex state management for asynchronous operations.

Usage examples

“How do I define a basic two-step workflow using the Upstash SDK?”: The agent provides a code snippet using the serve() function and context.run() to define sequential steps that persist across execution.
“How can I trigger a workflow from my existing backend code?”: The agent demonstrates initializing the Workflow Client with a QStash token and using the trigger() method to initiate the workflow URL.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/upstash/upstash-workflow-js/download

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

mkdir -p .agents/skills && unzip upstash-workflow-js.zip -d .agents/skills

Documentation by Upstash

Upstash Workflow SDK

Bundled docs and source

Before writing or debugging SDK code, check node_modules/@upstash/workflow/docs/ for bundled docs and node_modules/@upstash/workflow/src/ for readable TypeScript source. Read and search the relevant files when present; otherwise use the references in this skill.

Quick Start

The Upstash Workflow SDK lets you expose serverless workflow endpoints and run them reliably using QStash under the hood.

Install:

npm install @upstash/workflow

Define a simple workflow endpoint:

import { serve } from "@upstash/workflow";

export const { POST } = serve(async (context) => {
  await context.run("step-1", () => console.log("step 1"));
  await context.run("step-2", () => console.log("step 2"));
});

Trigger it from your backend:

import { Client } from "@upstash/workflow";

const client = new Client({ token: process.env.QSTASH_TOKEN! });
await client.trigger({ url: "https://your-app.com/api/workflow" });

Other Skill Files

These files contain the full documentation. Use them for details, patterns, and advanced behavior.

basics:
- basics/serve – How to expose workflow endpoints.
- basics/context – Full API for workflow context (steps, waits, webhooks, events, invoke, etc.).
- basics/client – Using the Workflow client to trigger, cancel, inspect, and notify runs.
features:
- features/invoke – Cross‑workflow invocation.
- features/reliability – Retries, failure callbacks, and DLQ.
- features/flow-control – Rate limits, concurrency, and parallelism.
- features/wait-for-event – Notify and wait-for-event patterns.
- features/webhooks – Webhook creation and consumption.
how to:
- how-to/local-dev – Local QStash dev server (auto via QSTASH_DEV=true) and tunneling.
- how-to/realtime – Realtime and human‑in‑the‑loop workflows.
- how-to/migrations – Migrating workflows safely.
- how-to/middleware – Adding middleware to workflows.
other files:
- rest-api – Low-level REST endpoints for interacting with QStash/Workflow.
- troubleshooting – Common debugging and environment issues.
- agents – Using Workflow with agents, orchestrators, and automation patterns.

Files

ATTRIBUTION.mdAdded by AutoGineer892 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md3.4 KiB
agents.md6.7 KiB
basics/client.md4.1 KiB
basics/context.md5.1 KiB
basics/serve.md2.4 KiB
features/flow-control.md3.9 KiB
features/invoke.md2.6 KiB
features/retries-failures-reliability.md6.3 KiB
features/wait-for-event.md2.8 KiB
features/webhooks.md2.5 KiB
how-to/local-dev.md5.0 KiB
how-to/middleware.md4.7 KiB
how-to/migrations.md4.8 KiB
how-to/realtime.md4.8 KiB
rest-api.md6.6 KiB
troubleshooting.md4.8 KiB

Requirements and compatibility

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 Node.js

Security

What our scanner noticed· Medium risk

Possible data-exfiltration endpoints

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

Shipping And Launch
Addy Osmani· Community
A comprehensive framework for managing safe, observable, and reversible production software deployments.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository113.9k
Quantized Export
Seth Hobson· Community
Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository42.3k
Deployment Pipeline Design
Seth Hobson· Community
Design robust, secure, and automated CI/CD pipelines with multi-stage promotion, approval gates, and progressive delivery strategies.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository42.3k
Gitops Workflow
Seth Hobson· Community
A guide to implementing GitOps workflows for Kubernetes using ArgoCD and Flux.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Spark Environment Setup
Seth Hobson· Community
Set up and troubleshoot ML training and inference environments on NVIDIA DGX Spark hardware.
Cloud and DevOpsClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository42.3k
Cloud Infrastructure Deployment Engineer
Seth Hobson· Community
An expert deployment engineer agent specializing in CI/CD pipelines, GitOps workflows, and advanced containerized deployment automation.
Cloud and DevOpsClaude Code
MITGitHub stars of the source repository42.3k