Langfuse

If you're running LLM applications in production, you need observability that understands tokens, costs, and prompt versions, not just HTTP requests. This skill covers Langfuse's tracing system with drop-in integrations for OpenAI, LangChain, and LlamaIndex. You get automatic instrumentation for LLM calls, prompt versioning you can deploy like feature flags, and eval pipelines for catching regressions. The patterns show real implementations, from basic trace setup to LLM-as-judge evaluation. Self-hosted or cloud, either works. Most valuable when you're past the prototype stage and need to understand why your costs spiked or which prompt version performs better.

skills.sh installs: 628
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill langfuse --agent claude-code

Installs into .claude/skills of the current project.

Files

Langfuse

Instrument an existing LLM application with traceable, minimized observations and versioned evaluation inputs. Modified by AAS maintainers on 2026-09-05 to replace mixed legacy SDK examples with a current, bounded setup procedure; existing source attribution is preserved.

When to Use

Use when an application already needs Langfuse tracing, prompt management or evaluation, or when debugging missing/duplicated spans. Do not add an observability service merely because an LLM is present; start from the incident or product decision the data must support.

Inputs and prerequisites

Installed Python or JS SDK version, framework and runtime lifecycle.
The explicitly authorized Langfuse project/endpoint, credentials supplied through the project’s secret mechanism, and data retention/access policy.
An allowlist of observable fields and a synthetic request that contains no private content.
A defined verifier: expected parent/child spans, status, timing, model/prompt version and flush behavior.