langfuse/skills

Agent Skills for Langfuse, the open source LLM engineering platform for tracing, prompt management, and evaluation

What it solves

It enables AI coding assistants (such as Claude Code and Cursor) to interact directly with the Langfuse platform. This removes the manual effort of looking up documentation, configuring tracing, or migrating data from other observability platforms when building LLM applications.

How it works

The project provides a set of "skills"—specialized instructions and tool definitions—that can be installed into AI agents. These skills allow the agent to use the Langfuse API to query and manage traces, prompts, and datasets, as well as follow best practices for instrumentation and migration.

Who it’s for

Developers using AI coding assistants who want to integrate Langfuse for LLM observability, prompt management, and evaluation into their development workflow.

Highlights

  • Direct API Integration: Allows agents to manage traces, prompts, and datasets via the Langfuse API.
  • Migration Tooling: Includes a specific skill to automate the transfer of historical traces, datasets, and prompts from platforms like LangSmith, Arize, or Braintrust.
  • Agent-Native Installation: Supports installation via Cursor plugins or the skills CLI.
  • Automated Instrumentation: Helps agents set up tracing, audit existing instrumentation, and configure CI/CD experiment gates.

Related

  • Project
    fractalbits-labs/fractalbits

    A high-performance, S3-compatible object storage system optimized for small object workloads in AI training and data analytics, featuring native atomic rename support.

  • Project
    usnistgov/dioptra

    A software test platform from NIST for assessing the trustworthy characteristics of AI, providing tools to design, execute, and track experiments to ensure safety, fairness, and reliability.

  • Project
    open-thoughts/OpenThoughts-Agent

    OpenThoughts‑Agent (OT‑Agent) is a research‑focused toolkit for generating training data, fine‑tuning, and evaluating small agentic language models. It bundles a datagen pipeline (Ray + vLLM), SFT support via LLaMA‑Factory, and a Harbor‑based evaluation framework, with launchers that work on SLURM clusters, cloud VMs (SkyPilot), or locally. The codebase is aimed at researchers building and benchmarking agentic LLMs.

  • Project
    praetorian-inc/augustus

    A Go-based LLM vulnerability scanner that tests models against 210+ adversarial attacks, including prompt injection and jailbreaks, to identify security weaknesses.