querying-mlflow-metrics

Enables AI coding assistants to search and navigate MLflow documentation for building, debugging, and evaluating GenAI applications.

Agent evaluation skill using MLflow for systematically evaluating and improving LLM agent output quality. Covers tool selection accuracy, answer quality, cost reduction, and end-to-end evaluation with datasets, scorers, and tracing.

Provides onboarding guidance for MLflow, helping AI coding assistants get started with MLflow's tracing, evaluation, and observability features.

Guides AI coding assistants in instrumenting applications with MLflow tracing for observability and debugging of GenAI workflows.

Teaches AI coding assistants how to retrieve and query MLflow traces for analyzing GenAI application performance and behavior.

Teaches AI coding assistants how to analyze MLflow traces for debugging and evaluating GenAI applications with MLflow's observability features.

An MLflow skill for analyzing tracing sessions, giving AI coding assistants deep knowledge of MLflow's tracing, evaluation, and observability for debugging GenAI applications.

A master dispatcher skill for MLflow that reads user intent and automatically routes to the appropriate sub-skill — covering tracing/instrumentation, agent evaluation, trace analysis, metrics querying, onboarding, and documentation search. It asks at most one clarifying question before dispatching, ensuring every MLflow task is handled by the most relevant specialized skill.