langfuse · davila7 — Claude Code skill: what it does, how to install
Adds LLM observability, prompt metrics, and trace logging to projects via Langfuse. Helps monitor LangChain or OpenAI workflows.
npx claude-code-templates@latest --skill ai-research/langfuseWhat langfuse does
This skill guides Claude Code in setting up LLM telemetry for Python and TypeScript applications. It covers instrumenting model calls, grouping interactions with user identifiers, and logging response scores. To use it, you need a Langfuse account (cloud-hosted or self-hosted), host credentials, and active LLM provider keys.
The skill outlines integration patterns such as the drop-in langfuse.openai wrapper and the LangChain CallbackHandler. It also flags operational pitfalls. In serverless setups, omitting langfuse.flush() drops batched traces before the process exits.
What it helps with
- instrument model calls with traces and spans
- track token expenditures and response latency
- attach LangChain callbacks to log chain executions
- record user feedback scores on generated outputs
Example prompts for the agent
- Add Langfuse tracing to our OpenAI completion script.
- Configure a LangChain CallbackHandler with user and session metadata.
- Show how to flush pending traces inside an AWS Lambda handler.
How to install langfuse
1claude-code-templates
npx claude-code-templates@latest --skill ai-research/langfuse2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill langfuse -a claude-code3Manually: put the files in place
~/.claude/skills/langfuse/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/langfuse/
Manually: put the files in place
.agents/skills/langfuse/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/langfuse/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates langfuse2Manually: put the files in place
.github/skills/langfuse/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/langfuseManually: put the files in place
.devin/skills/langfuse/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about langfuse
How to install langfuse in Claude Code?
Run npx claude-code-templates@latest --skill ai-research/langfuse in your terminal. Alternatively, install it with npx skills add davila7/claude-code-templates --skill langfuse -a claude-code.
What does the langfuse skill do?
It instructs the assistant on implementing Langfuse tracing, dataset tracking, and prompt scoring. It focuses on Python and TypeScript stacks using OpenAI or LangChain.
What prerequisites are required for Langfuse integration?
You need a self-hosted or cloud Langfuse account with public and secret keys, plus working API keys for your model providers.
Similar skills
All skills for AI and ML →langfuse by other authors comes first.