mlops-workflows — Claude Code skill: what it does, how to install
Integrates MLflow practices into your AI coding assistant. The skill guides experiment tracking, model registry management, and parameter logging.
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a claude-codeWhat mlops-workflows does
The skill provides step-by-step guidance for organizing machine learning lifecycles with MLflow. It directs the assistant to log run parameters and package pipelines with MLproject configs. During training, the agent infers model signatures and records metadata systematically.
Hyperparameter tuning uses nested runs. This structure separates parent search jobs from child trials when running GridSearchCV. Models are committed to the MLflow Registry, where deployment aliases like production mark release candidates.
Logging fails if an MLflow tracking server is not reachable at http://localhost:5000 or configured locally. You need Python 3.8 or newer alongside MLflow 2.0+ and scikit-learn installed in your environment.
What it helps with
- track training metrics and model parameters in MLflow
- configure nested runs for hyperparameter search
- assign production aliases in the MLflow model registry
- enable automatic logging for scikit-learn models
Example prompts for the agent
- Configure MLflow tracking for my random forest regressor training run.
- Set up nested MLflow runs to capture each step of hyperparameter tuning.
- Register the trained model in MLflow and tag it with the production alias.
How to install mlops-workflows
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a claude-code2Manually: put the files in place
~/.claude/skills/mlops-workflows/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/mlops-workflows/
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a codex2Manually: put the files in place
.agents/skills/mlops-workflows/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a cursor2Manually: put the files in place
.cursor/skills/mlops-workflows/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install manutej/luxor-claude-marketplace mlops-workflows2Manually: put the files in place
.github/skills/mlops-workflows/SKILL.md1Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a gemini-cli2Platform CLI
gemini skills install https://github.com/manutej/luxor-claude-marketplace --path plugins/luxor-data-engineering/skills/mlops-workflowsManually: put the files in place
.devin/skills/mlops-workflows/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about mlops-workflows
How do I install mlops-workflows in Claude Code?
Run npx skills add manutej/luxor-claude-marketplace --skill mlops-workflows -a claude-code in your terminal.
What does mlops-workflows do?
It teaches your coding agent how to implement MLflow tracking, register models, and structure reproducible ML projects.
What are the prerequisites for this skill?
You need Python 3.8+, MLflow 2.0+, and scikit-learn. You also need a configured tracking URI such as a local server at http://localhost:5000.
