Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Tracing and evaluating LLM apps with Langfuse v1.0.0

Use this resource to set up tracing and evaluation for an LLM application with Langfuse

New

  • 408 downloads
  • 148 likes
  • 226 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-observability-tracing-3

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent integrates Langfuse into your OpenAI or LangChain application, traces the calls, manages prompt versions and prepares evaluations. It flags common pitfalls, such as traces not flushed in serverless environments. You get observability you can use to debug and track costs.

Mostly picked by

Updated November 2, 2026

Card for the “Tracing and evaluating LLM apps with Langfuse” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: capabilities, requirements and knowledge modules
  • sub-skills/openai-integration.md and langchain-integration.md: OpenAI and LangChain integrations

Good fit for

  • Your AI agent answers badly and you cannot tell which step fails
  • You want to track cost per session in your LLM app

Not for

    Tags

    • langfuse
    • observability
    • traces
    • evaluation
    • prompts

    About

    You say

    “Add Langfuse tracing to my OpenAI call and show me how to track cost per session.”

    Card for the “Tracing and evaluating LLM apps with Langfuse” skill

    Skill published by dokhacgiakhoa under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to set up tracing and evaluation for an LLM application with Langfuse
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE2.4 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.6 KB
    • sub-skills/basic-tracing-setup.md1.3 KB
    • sub-skills/langchain-integration.md1.3 KB
    • sub-skills/no-usersession-ids.md0.5 KB
    • sub-skills/not-flushing-in-serverless.md0.2 KB
    • sub-skills/openai-integration.md1.1 KB
    • sub-skills/tracing-everything.md0.2 KB

    Origin and licence

    Listed unmodified

    Author
    dokhacgiakhoa
    Source
    github.com/dokhacgiakhoa/agent-skills-4-vibe-coding-cli/tree/c4a059bbf7a8d6b2162071f0fbfe74053faa6d20/.agent/skills/langfuse
    Licence
    MIT

    Notice

    « langfuse » (dokhacgiakhoa, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.