claude-langfuse-plugin

Plan or operate a self-hosted Langfuse deployment — sizing, scaling, backups, upgrades, security.

Design and set up a Langfuse evaluation — method choice, scores, datasets/experiments, online/offline.

Check a Langfuse connection/project is healthy — auth, ingestion, and recent activity.

Build or query Langfuse monitoring — dashboards, metrics (cost/latency/quality/volume), alerting.

Guide Langfuse onboarding and setup — deployment choice, keys, first trace, prod-readiness.

Designs a complete Langfuse evaluation strategy for an LLM application — choosing methods, defining scores, shaping datasets/experiments, and planning online + offline evaluation. Use when the user asks to "design an eval strategy", "figure out how to evaluate my agent/RAG/chatbot", "what should I measure and how", or wants a structured evaluation plan rather than ad-hoc scoring. Explores the codebase when available to ground the plan in the actual application.

Diagnoses why a Langfuse setup isn't working — traces not appearing, auth/connection errors, region/key mismatches, SDK init problems, flush-on-exit issues. Use when the user says "my traces aren't showing up", "Langfuse auth is failing", "can't connect to Langfuse", "is my Langfuse setup working", or a first-trace check fails. Read-only: it diagnoses and recommends, never mutates data.

Reviews Langfuse traces/observations at scale to find, classify, and quantify failure modes, then recommends fixes and regression test cases. Use when the user says "review my traces", "what's going wrong in production", "analyze failures in my Langfuse traces", "find error patterns", or wants systematic error analysis rather than reading traces one by one. Read-only: it analyzes and recommends, never mutates data.

Operating a self-hosted Langfuse deployment — architecture, sizing, scaling, backups, upgrades, and security. Use whenever the user is running or planning to run Langfuse on their own infrastructure: "operate / run self-hosted Langfuse", "deploy Langfuse on Kubernetes / Docker / AWS / GCP / Azure", "Langfuse sizing / resource requirements", "scale Langfuse / ingestion throughput", "back up Langfuse", "upgrade Langfuse / background migrations", "Langfuse SSO / encryption / VPC / air-gapped", or "Langfuse production deployment". Owns HOW to run self-hosted Langfuse well; the self-host-vs-Cloud and tier decision lives in the `langfuse-setup` skill, and exact configs in live docs.

Designs and runs LLM evaluation with Langfuse — the strategy and workflow layer for scoring quality, building datasets, and running experiments. Use whenever the user is evaluating LLM output quality with Langfuse: "evaluate my LLM app", "which eval method should I use", "set up LLM-as-a-judge", "create a dataset / run an experiment", "score my traces", "offline vs online evaluation", "test prompt changes before deploying", "build a regression test set", or interpreting experiment results. Owns eval STRATEGY and the datasets/experiments/scores workflow; defers judge calibration and CI/CD experiment code to the vendored `langfuse` skill, and exact SDK code to live docs.

Monitors and analyzes LLM application data already in Langfuse — dashboards, metrics, and alerting for cost, latency, quality, and volume. Use whenever the user wants to observe or report on production Langfuse data: "monitor my LLM app", "build a Langfuse dashboard", "track cost / latency / quality over time", "Langfuse metrics API", "score analytics", "set up a spend alert", "alert me when costs spike", "dashboard for production monitoring", or interpreting usage/cost/quality trends. Owns operating-the-data (dashboards/metrics/alerting); defers instrumentation to the vendored `langfuse` skill and score/evaluator design to the `langfuse-evaluation` skill.

Orchestrates Langfuse adoption decisions and production-readiness — the planning the official `langfuse` skill doesn't cover. Use whenever the user is deciding HOW to adopt Langfuse or whether their setup is ready: "set up Langfuse", "Langfuse Cloud or self-host", "which Langfuse region", "configure Langfuse keys/env", "is my Langfuse setup production ready", "Langfuse prod checklist", "my traces aren't showing up", or planning a Langfuse rollout. Defers instrumentation CODE to the vendored `langfuse` skill — this skill owns the decisions, order, and verification around it.

Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.

1 hook across 1 event