This skill should be used when the user asks to "query Langfuse traces", "show sessions", "check LLM costs", "analyse token usage", "view observations", "get scores", "create score", "add score to trace", "query metrics", or mentions Langfuse, traces, or LLM observability. Also triggers on requests to analyse API latency, debug LLM calls, or investigate model performance. Use for prompt management tasks like "list prompts", "get prompt", "create prompt", "update prompt labels", or "deploy prompt to production". Use for dataset management tasks like "list datasets", "create dataset", "add dataset item", "view dataset runs", or "manage evaluation datasets".
View on GitHubtavva/ben-claude-plugins
langfuse
plugins/langfuse/skills/langfuse-cli/SKILL.md
January 21, 2026
Select agents to install to:
npx add-skill https://github.com/tavva/ben-claude-plugins/blob/main/plugins/langfuse/skills/langfuse-cli/SKILL.md -a claude-code --skill langfuse-cliInstallation paths:
.claude/skills/langfuse-cli/# Langfuse CLI (`lf`) Command-line interface for the Langfuse LLM observability platform. Query traces, sessions, observations, scores, and metrics. Manage prompts with versioning and labels. Manage datasets for evaluation. ## Quick Reference ``` lf traces list [OPTIONS] # List traces with filters lf traces get <ID> # Get specific trace (--with-observations) lf sessions list [OPTIONS] # List sessions lf sessions show <ID> # Show session details (--with-traces) lf observations list [OPTIONS] # List observations (spans/generations/events) lf observations get <ID> # Get specific observation lf scores list [OPTIONS] # List scores lf scores get <ID> # Get specific score lf scores create [OPTIONS] # Create a new score lf metrics query [OPTIONS] # Query aggregated metrics lf prompts list [OPTIONS] # List prompts lf prompts get <NAME> # Get prompt (by label or version) lf prompts create-text # Create text prompt (-m for commit message) lf prompts create-chat # Create chat prompt (-m for commit message) lf prompts label <NAME> <VER> # Set labels on prompt version lf prompts delete <NAME> # Delete prompt lf datasets list [OPTIONS] # List datasets lf datasets get <NAME> # Get dataset by name lf datasets create <NAME> # Create a new dataset lf datasets items [OPTIONS] # List dataset items (--dataset to filter) lf datasets item-get <ID> # Get dataset item by ID lf datasets item-create # Create dataset item (--dataset, --input required) lf datasets runs <DATASET> # List runs for a dataset lf datasets run-get <DS> <RUN> # Get a specific run ``` ## Common Tasks ### View Recent Traces ```bash lf traces list --limit 20 ``` ### Filter Traces by Time ```bash # Today's traces lf traces list --from "$(date -u +%Y-%m-%dT00:00:00Z)" # Last 24 hours lf traces list --from "$(date -u -v-1d +%Y-%m-%dT%H:%M:%SZ)" # Specific date range lf traces list -