---
date: 2026-05-26
badge: Launch Week 5 🚀
title: Langfuse agent skill
description: Your agent's playbook for production-ready LLM apps
author: Lotte, Marlies
---
> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).
We're releasing our [Langfuse skill](/docs/api-and-data-platform/features/agent-skill) to give AI coding agents the expertise to leverage Langfuse for robust observability and evaluation workflows. It follows the open [Agent Skills](https://github.com/anthropics/skills) standard and works with Claude Code, Cursor, Codex, and others.
## What are skills and why do they work?
Skills are focused bundles of instructions, scripts, and resources that agents load only when relevant. They encode proven practices for observability and evaluation while keeping context lean.
## Why use skills?
Skills turn Langfuse into a headless platform you control through natural language. You describe the job, and your agent follows a research-backed playbook in your editor. Ask your agent to:
- Show me the last 10 traces with a score below 0.5. Create a dataset called "edge-cases" and add these traces to it.
- Migrate the system prompt in src/agent.ts to Langfuse prompt management.
- My human annotators identified five recurring error cases. Help me set up an evaluator for each.
The skill makes coding agents more effective at working with Langfuse. To illustrate this, here is an example of how an agent instruments the same application without vs. with the skill:
> **Guide: [LLM-as-a-judge calibration](/guides/llm-as-a-judge-calibration-skill)**
>
> One specific use case we added to the skill is the judge calibration workflow. Given a ground-truth dataset, it will check whether your LLM-as-a-Judge behaves the way you'd expect, and iterate until it does.
## Installation
Install the [Langfuse Agent Skill](https://github.com/langfuse/skills) to let your coding agent access all Langfuse features.
Ask your coding agent to install the skill by pointing to the [GitHub repository](https://github.com/langfuse/skills).
```txt filename="Agent instruction"
"Install the Langfuse Agent Skill from github.com/langfuse/skills."
```
Langfuse has a [Cursor Plugin](https://cursor.com/docs/plugins) that includes the skill automatically.
Install via npm ([skills CLI](https://www.npmjs.com/package/skills)):
```bash
npx skills add langfuse/skills --skill "langfuse"
```
If you want to target a specific agent directly:
```bash
npx skills add langfuse/skills --skill "langfuse" --agent ""
```
Alternatively you can manually clone the skill
1. Clone repo somewhere stable
```bash
git clone https://github.com/langfuse/skills.git /path/to/langfuse-skills
```
2. Make sure your agent's skills dir exists
```bash
mkdir -p /path/to//skills
```
3. Symlink the skill folder
```bash
ln -s /path/to/langfuse-skills/skills/langfuse /path/to//skills/langfuse
```
The `langfuse/skills` repository is open source, and contributions are welcome.
## Learn more
- [Langfuse CLI](/docs/api-and-data-platform/features/cli) — the CLI the skill uses under the hood
- [Making agents fall in love with Langfuse](/blog/2026-02-13-will-you-be-my-cli) — the full story behind the skill, CLI, and agent platform
- [Prompt iteration](/blog/2026-02-16-prompt-improvement-claude-skills) — analyze feedback and iteratively improve prompts
- [Error analysis](/blog/2025-11-12-evals) — systematically evaluate and debug LLM applications
---
## Agent Instructions
This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2026-05-26-langfuse-agent-skill.md`.
### Querying these docs
If the answer is not on this page, query the documentation instead of guessing:
- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:
```bash
curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
```
- **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).
### Before writing Langfuse code
- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api `) to read or write traces, prompts, datasets, and scores from the terminal.
Found an error in these docs? Please open an issue at .