Agent skill · data analytics · jeremylongshore
langfuse-observability
Set up comprehensive observability for Langfuse with metrics, dashboards,
Why this skill is useful
Adds executable scripts for Prometheus metrics and Grafana dashboards specifically tailored for Langfuse integration monitoring.
What it needs
Requires grafana, prometheus installed locally. Requires langfuse account access. About 4k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Langfuse Observability Overview 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. Prerequisites Langfuse SDK integrated and producing traces For custom metrics: Prometheus + Grafana (or compatible stack) For Langfuse analytics: access to the Langfuse UI dashboard Instructions Step 1: Langfuse Built-In Dashboards Langfuse provides pre-built dashboards in the UI at https://cloud.langfuse.com (or your self-hosted URL): Overview: Total traces, generations, scores, and errors Cost Dashboard: Token usage and costs over time, broken down by model, user, session Latency Dashboard: Response times across models and user segments Custom Dashboards: Build your own with the query engine (multi-level aggregations, filters by user/model/tag) Accessing via Metrics API: Step 2: Prometheus Metrics for Your App Track the health of your Langfuse integration with custom Prometheus metrics: Step 3: Expose Metrics Endpoint Step 4: Prometheus Scrape Config Step 5: Grafana Dashboard Step 6: Alert Rules Key Metrics Reference Metric Type Purpose -------- ------ --------- langfusetracescreatedtotal Counter LLM request throughput + error rate langfusegenerationdurationseconds Histogram Latency percentiles langfusetokenstotal Counter Token usage tracking langfusecostusdtotal Counter Budget monitoring langfuseflusherrorstotal Counter SDK health Error Handling Issue Cause Solution ------- ------- ---------- Missing metrics No instrumentation Use the tracedLLM wrapper High cardinality Too many label values Limit to model + status only Alert storms Thresholds too low Start conservative, tune over time Metrics endpoint slow Large registry Use summary instead of histogram for high-volume Output Produce an observability receipt containing the dashboard URL, the time range, P95 latency, error rate, token/cost total, and alert state. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/langfuse-observability