Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langfuse-reference-architecture
Production-grade Langfuse architecture patterns and best practices.
Passed 13 of 23 test cases with the skill, and 8 of 23 without it.
and 5 more in the full report
5 fixed8 passed either way10 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
When initializing NodeSDK in src/lib/tracing.ts for singleton OpenTelemetry tracing, what export interval and batch size settings should be passed to LangfuseSpanProcessor by default?
| Checked | Without skill | With skill |
|---|---|---|
| Passes exportIntervalMillis of 5000 to LangfuseSpanProcessor. | Missed | Passed |
| Passes maxExportBatchSize of 50 to LangfuseSpanProcessor. | Missed | Passed |
The instructions your model reads when the skill loads.
Production-grade architecture patterns for Langfuse LLM observability: singleton SDK, context propagation with AsyncLocalStorage, cross-service trace correlation, multi-environment configurations, and scale strategies.
@langfuse/tracing, @langfuse/otel, @opentelemetry/sdk-node| Tier | Scale | Architecture | Langfuse Host |
|---|---|---|---|
| Starter | < 100K traces/day | Direct SDK, Cloud | Langfuse Cloud |
| Growth | 100K-1M traces/day | Singleton + batching | Cloud or Self-hosted |
| Enterprise | 1M+ traces/day | Queue-buffered + sampling | Self-hosted (HA) |
// src/lib/tracing.ts -- Single module for all tracing
import { LangfuseClient } from "@langfuse/client";
import { LangfuseSpanProcessor } from "@langfuse/otel";
import { NodeSDK } from "@opentelemetry/sdk-node";
import { AsyncLocalStorage } from "async_hooks";
// Singleton OTel SDK
let sdk: NodeSDK | null = null;
export function initTracing() {
if (sdk) return sdk;
sdk = new NodeSDK({
spanProcessors: [
new LangfuseSpanProcessor({
test cases passed, vs 8 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.