Analytics & Monitoring Agent Skills for Claude Desktop

vLLM: high-throughput LLM serving, OpenAI API, quantization.

List, inspect, enable, disable, and resync Kibana Streams via the REST API.

Retrieves structured data from global financial markets, enterprise registries, academic journals, and Chinese legal databases.

Build async video generation workflows with Kling AI using queues, state

Implement budget limits, usage alerts, and spending controls for Kling

Build LangChain agents with tools for autonomous task execution.

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration.

Complex migration strategies for LangChain applications.

Install and configure Langfuse SDK authentication for LLM observability.

LLM observability platform for tracing, evaluation, prompt management, and cost tracking.

Compose LangGraph 1.0 subgraphs correctly \u2014 shared state key propagation,\n\

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio.

LLM observability platform for tracing, evaluation, and monitoring.

[Beta] Cross-session analysis of accumulated .learnings/ files.

INVOKE THIS SKILL when building evaluation pipelines for LangSmith.

Build voice AI agents with LiveKit Agents SDK.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.

Use proactively whenever LLM API costs come up -- or should.

Review code for correct logging and error handling patterns.

Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning…