Trace LLM applications
Query application traces and scores using the Langfuse CLI.
Equip AI coding agents to trace LLM applications, manage prompts, and package custom agent skills.
Official Agent Skills published by Langfuse
Use these Agent Skills to query Langfuse traces and run evaluations. Manage your system prompts directly in your coding workspace.
Query application traces and scores using the Langfuse CLI.
Organize and migrate codebase prompts directly into prompt management.
Create custom Claude Code skills using standardized YAML markdown templates.
Official Agent Skills published by Langfuse.
Guides developers in creating, structuring, and optimizing custom Claude Code Skills to extend Claude's agentic capabilities.
Connects Claude to the Langfuse API and documentation to streamline LLM tracing, prompt management, evaluation, and application instrumentation.
Add Langfuse Skills to agents that support the Agent Skills format, including Claude, Claude Code, Codex, and OpenCode. Install manually from source, or use MCP Market Hub to sync and share them with your team.
Add official skills once, keep them current across your agents, and share the same skill set with your team.
Prefer manual control? Download the skills from source, then follow the install guide for your agent.
langfuse/skillsReal workflows powered by Langfuse skills.
Migrate codebase prompts
Move hardcoded system prompts from your local application into prompt management.
Trace execution errors
Debug LLM chains by querying execution traces and user feedback scores.
Bootstrap custom skills
Create a new Claude Code skill using standardized folder layouts and metadata templates.
Verified, first-party skills from other brands you know.