CtrlK
BlogDocsLog inGet started
Tessl Logo

langfuse-prod-checklist

Langfuse production readiness checklist and verification. Use when preparing to deploy Langfuse to production, validating production configuration, or auditing existing setup. Trigger with phrases like "langfuse production", "langfuse prod ready", "deploy langfuse", "langfuse checklist", "langfuse go live".

86

0.96x
Quality

83%

Does it follow best practices?

Impact

93%

0.96x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Evaluation results

100%

12%

Langfuse Integration Setup for Production API Service

Singleton client and production SDK configuration

Criteria
Without context
With context

Singleton pattern used

100%

100%

getLangfuse returns same instance

100%

100%

flushAt set to 25-50

100%

100%

flushInterval set to 5000

100%

100%

requestTimeout set to 15000

0%

100%

Environment variables used for keys

100%

100%

Module is importable

100%

100%

No per-request instantiation remains

100%

100%

TypeScript types preserved

100%

100%

97%

-3%

Production-Ready Langfuse Tracing for an Order Processing Service

Graceful shutdown and safe error handling

Criteria
Without context
With context

SIGTERM handler added

100%

100%

SIGINT handler added

100%

100%

beforeExit or equivalent flush

100%

100%

Tracing errors caught internally

100%

100%

Application errors still propagate

100%

100%

fn() still called on trace failure

100%

100%

No new errors introduced

100%

62%

TypeScript compiles cleanly

100%

100%

84%

-16%

Pre-Deployment Gate Script for Langfuse-Instrumented Service

Pre-deployment verification script and key validation

Criteria
Without context
With context

Checks LANGFUSE_PUBLIC_KEY env var

100%

100%

Checks LANGFUSE_SECRET_KEY env var

100%

100%

Validates pk-lf- prefix on public key

100%

75%

Validates sk-lf- prefix on secret key

100%

75%

API connectivity check included

100%

71%

Trace creation check included

100%

57%

Structured pass/fail report printed

100%

100%

Exits non-zero on any failure

100%

100%

Script is standalone TypeScript

100%

100%

Repository
jeremylongshore/claude-code-plugins-plus-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.