Langfuse just got faster →
DocsAPI & Data PlatformFeaturesAgent Skill

Langfuse Agent Skill

The Langfuse agent skill helps AI coding agents use Langfuse effectively. It follows the open Agent Skills standard and works with Claude Code, Cursor, Windsurf, and other compatible agents. The skill is open source on GitHub.

Why use it

Coding agents produce significantly better results with the skill installed, because they are conditioned to follow best practices. A coding agent with access to the skill has an opinionated view on what good looks like, based on Langfuse's knowledge.

The skill is a self-contained folder with a SKILL.md entrypoint describing general rules and instructions on using documentation, plus reference docs for specific workflows that are filled with specific best practices:

SKILL.md
cli.md
instrumentation.md
prompt-migration.md
...

The skill uses a progressive disclosure model: the frontmatter is always loaded into the agent's context so it knows when the skill is relevant, but the full instructions and reference docs are only loaded on demand. This keeps context usage low while giving agents access to specialized knowledge.

Install

Install the Langfuse AI Skill to let your coding agent access all Langfuse features.

Ask your coding agent to install the skill by pointing to the GitHub repository.

"Install the Langfuse AI skill from github.com/langfuse/skills."

Langfuse has a Cursor Plugin that includes the skill automatically.

Install via npm (skills CLI):

npx skills add langfuse/skills --skill "langfuse"

If you want to target a specific agent directly:

npx skills add langfuse/skills --skill "langfuse" --agent "<agent-id>"
Alternatively you can manually clone the skill
  1. Clone repo somewhere stable
git clone https://github.com/langfuse/skills.git /path/to/langfuse-skills
  1. Make sure your agent's skills dir exists
mkdir -p /path/to/<agent-skill-root>/skills
  1. Symlink the skill folder
ln -s /path/to/langfuse-skills/skills/langfuse /path/to/<agent-skill-root>/skills/langfuse

Once installed, you can prompt your agent with what you want to do. A couple of examples:

  • Show me the last 10 traces with a score below 0.5
  • Create a dataset called "edge-cases" and add these 3 items to it
  • Migrate the system prompt in src/agent.ts to Langfuse prompt management

Resources


Was this page helpful?