Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jeremylongshore/langfuse-observability
Set up comprehensive observability for Langfuse with metrics, dashboards, and alerts.
Passed 15 of 22 test cases with the skill, and 5 of 22 without it.
and 14 more in the full report
10 fixed5 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a YAML alert rule named `HighLLMLatency` that fires when P95 latency exceeds 10 seconds for 5 minutes.
| Checked | Without skill | With skill |
|---|---|---|
| Evaluates expression histogram_quantile(0.95, rate(langfuse_generation_duration_seconds_bucket[5m])) > 10. | Missed | Passed |
| Configures duration parameter for to 5m. | Passed | Passed |
The instructions your model reads when the skill loads.
Set up monitoring for your Langfuse integration: Prometheus metrics for trace/generation throughput, Grafana dashboards, alert rules, and integration with Langfuse's built-in analytics dashboards and Metrics API.
Langfuse provides pre-built dashboards in the UI at https://cloud.langfuse.com (or your self-hosted URL):
Accessing via Metrics API:
import { LangfuseClient } from "@langfuse/client";
const langfuse = new LangfuseClient();
// Fetch aggregated metrics programmatically
const traces = await langfuse.api.traces.list({
fromTimestamp: new Date(Date.now() - 3600000).toISOString(), // Last hour
limit: 100,
});
console.log(`Traces in last hour: ${traces.data.length}`);
// Get observations with cost data
const observations = await langfuse.api.observations.list({
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.