Agent Skills
Inngest Skills provides pre-built agent skills for AI coding agents like Claude Code, Cursor, and Windsurf. They give your coding agent comprehensive, up-to-date guidance on building reliable applications with Inngest — from initial setup to advanced flow control.
Inngest Skills is open source at github.com/inngest/inngest-skills.
Why use agent skills?
Instead of relying on an AI model's training data (which may be outdated or incomplete), agent skills provide:
- Current API knowledge — Accurate function signatures, configuration options, and best practices
- Step-by-step guidance — Structured instructions for common Inngest patterns
- Workflow templates — Proven patterns for background jobs, scheduled tasks, and event-driven workflows
Installation
npx skills add inngest/inngest-skills
For other agents, reference the repository directly or clone it to your agent's skills directory. Each skill is self-contained with full documentation in its SKILL.md file.
Available skills
| Skill | Description | What it covers |
|---|---|---|
| inngest-setup | Set up Inngest in a TypeScript project | SDK installation, client config, environment variables, dev server |
| inngest-events | Design and send Inngest events | Event schema, naming conventions, idempotency, fan-out patterns, system events |
| inngest-durable-functions | Create and configure durable functions | Triggers, step execution, memoization, cancellation, error handling, retries |
| inngest-steps | Use step methods to build durable workflows | step.run, step.sleep, step.waitForEvent, loops, parallel execution |
| inngest-flow-control | Configure flow control for functions | Concurrency limits, throttling, rate limiting, debounce, priority, batching |
| inngest-middleware | Create middleware for cross-cutting concerns | Middleware lifecycle, dependency injection, built-in middleware |
Language support
These skills are currently focused on TypeScript. Core concepts like events, steps, and flow control apply across all Inngest SDKs, but code examples and setup instructions are TypeScript-specific.
For Python or Go, refer to the Inngest documentation and llms.txt for language-specific guidance.
Combine with Dev Server MCP
For the best AI development experience, use agent skills alongside the Inngest Dev Server MCP integration. Together they provide:
- Skills give your agent knowledge of how to write correct Inngest code
- MCP gives your agent the ability to interact with your running dev server — list functions, send events, and monitor runs
This enables a complete write, test, and debug loop powered by your coding agent.