skills.rest
Blackkadder
BlackkadderCOMMUNITY
Explore all skills by this author →
GitHub

mlflow-onboarding

Detect MLflow project type and recommend quickstart tutorials and integration steps.

Updated Mar 19, 2026
Search Tags:#onboarding#integration#tracing#mlflow#experiment-tracking#genai#autologging
One-click install
npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill mlflow-onboarding-blackkadder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mlflow-onboarding
Source: https://github.com/Blackkadder/databricks-apps-and-agents-workshop/tree/main/.claude/skills/mlflow-onboarding
Command: npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill mlflow-onboarding-blackkadder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps users get started with MLflow by determining whether their project is a GenAI application or a traditional ML/deep learning workflow and guiding them through the appropriate quickstarts and integration steps so they can capture traces, experiments, and model artifacts correctly from the start.

Core Features & Use Cases

  • Use case detection: Inspect code patterns or experiment tags to classify projects as GenAI (LLM/agent-focused) or traditional ML and choose the right onboarding path.
  • Targeted quickstarts: Recommend GenAI tutorials for tracing, evaluation, and prompt/version tracking or ML tutorials for experiment tracking, autologging, and model deployment.
  • Integration guidance & verification: Provide code-level integration steps (autologging, custom tracing, experiment configuration) and verification commands for confirming traces and runs appear in MLflow.
  • Use Case Example: For an LLM-powered chatbot, configure MLflow tracing and autologging for the LLM provider and demonstrate mock traces; for a PyTorch training script, enable autologging and verify runs and artifacts.

Quick Start

Tell me whether you are building a GenAI application or a traditional ML model and ask me to set up MLflow tracing or tracking for your project, including an experiment ID if available.

Frequently Asked Questions about mlflow-onboarding

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up MLflow experiment tracking for a traditional ML project?▼

To set up MLflow experiment tracking for traditional ML, enable autologging in your training scripts like PyTorch, configure your experiment, and verify that runs and model artifacts appear in the MLflow UI.

What is the best way to add LLM tracing to a GenAI application?▼

The best way to add LLM tracing to GenAI applications is configuring MLflow custom tracing and autologging for your LLM provider, enabling you to capture and verify mock traces and prompt versions in the UI.

Can MLflow autologging detect whether my project is GenAI or traditional ML?▼

Yes, MLflow onboarding detects your project type by inspecting code patterns and experiment tags, classifying it as GenAI or traditional ML to recommend the appropriate autologging or custom tracing integration path.

Does MLflow tracing work with LLM-powered chatbots for prompt version tracking?▼

Yes, MLflow tracing works with LLM-powered chatbots by configuring tracing and autologging for the LLM provider, which captures mock traces, evaluates performance, and tracks prompt versions and runs in the UI.

How do I verify that my MLflow runs and traces are being logged correctly?▼

You verify MLflow runs and traces by running specific verification commands after configuring autologging or custom tracing, confirming that experiment runs, model artifacts, and LLM traces appear in the MLflow UI.

When should I use custom tracing instead of autologging for experiment tracking?▼

You should use custom tracing instead of autologging when working with GenAI applications requiring specific LLM agent tracing and evaluation, whereas traditional ML workflows typically rely on standard autologging for runs and artifacts.

Related Skills

Explore More Data & Analytics Skills→
slysikslysik

mlflow-onboarding

Identify MLflow use cases and recommend quickstart tutorials and integration steps.

Community
Intermediate
thbraetthbraet

experiment-compare

Compare MLflow experiment runs across metrics, hyperparameters, tags, and artifacts.

Community
Intermediate
curiositechcuriositech
181

llm-router

Select optimal LLM models and providers based on task complexity and cost.

Official
Advanced
ice-droid-99ice-droid-99

mlflow-onboarding

Detect GenAI versus traditional ML use cases and guide MLflow onboarding.

Community
Intermediate