What problem does it solve? Working with Langfuse requires up-to-date knowledge of its fast-changing APIs, SDKs, and documentation. This Skill gives you programmatic access to Langfuse data (traces, prompts, datasets, scores, sessions) through the langfuse-cli and reliable methods to fetch current Langfuse documentation, so you never implement from outdated memory. ## Core Features & Use Cases - CLI-based API access: Query and modify any Langfuse resource (traces, observations, scores, datasets, prompts) using npx langfuse-cli with schema discovery and credential handling. - Documentation retrieval: Access Langfuse docs via llms.txt index, markdown page fetching, and a search API covering docs plus GitHub issues and discussions. - Use-case playbooks: Dedicated references for instrumenting applications, migrating prompts to Langfuse, capturing user feedback as scores, upgrading SDKs, calibrating LLM-as-a-Judge evaluators, running error analysis on traces, and setting up CI/CD experiment gates. - Use Case: You want to debug why your LLM app's outputs degraded. The Skill pulls recent traces via the CLI, guides you through a structured error analysis with annotation queues, and helps you set up an evaluator — all using current Langfuse APIs. ## Quick Start Ask the assistant to list your recent Langfuse traces or fetch the Langfuse documentation page for the feature you are implementing.
