---
date: 2026-11-03
title: Skill Management in Langfuse
description: Collaborate and version AI agent skills in Langfuse, and connect them with your agent traces. Now available in beta.
badge: Beta
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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).

## Skill management in Langfuse

Next to prompt management, Langfuse now also offers skill management. Teams can centrally store and iterate on skills together. Skill management is also supported via API, CLI, MCP and SDKs.

![The refund-policy skill with version history, labels, supporting files, and the Files and Usage tabs.](/images/changelog/2026-11-03-skill-management-editor.png)

## Connect skills with your traces

With [skill tracing configured](/docs/skill-management/tracing), generations show the reported skill list, with links to each version.

![A generation reporting four available skills and a request for refund-policy v1 in the Preview view.](/images/changelog/2026-11-03-skill-management-generation.png)

Traced skill-loading tool calls show which files the agent read. Open **Preview → Skills** on a successful call to see the version and file paths. The skill's **Usage** tab combines usage counts, file loads, and linked observations.

![A loadSkill tool call showing refund-policy v1 and the loaded SKILL.md file in the trace's Preview view.](/images/changelog/2026-11-03-skill-management-tool-load.png)

## Get Started with skill management

See the [Skill Management docs](/docs/skill-management/overview) or [create your first skill](/docs/skill-management/get-started).

<!-- agent-instructions -->

---

## 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/2026-11-03-skill-management.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**: <https://langfuse.com/llms.txt>, 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 <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.