Automates CRISP-DM data science workflows in Jupyter notebooks with MLflow tracking.
npx skills add https://github.com/Ming-Kai-LC/fyp-project --skill fyp-jupyter
Please help me install this Agent Skill. Skill: fyp-jupyter Source: https://github.com/Ming-Kai-LC/fyp-project/tree/main/FYP_Code/.claude/skills/fyp-jupyter Command: npx skills add https://github.com/Ming-Kai-LC/fyp-project --skill fyp-jupyter
This Skill provides a complete, phase-based data science research workflow for Jupyter notebooks, enabling you to plan, run, and document Final Year Projects with reduced manual effort.
For example, a 10-week data science project would use this Skill to structure activities and maintain an organized ML experiment log.
Use this skill to start a guided data science workflow in your Jupyter project, enabling MLflow tracking and weekly planning.
High-intent search queries and answers about installing and using this skill.
A structured data science workflow in Jupyter uses phase-based guidance across exploration, experimentation, analysis, and documentation. This Skill automates planning and execution following CRISP-DM methodology, providing actionable checklists and templates for each phase to reduce manual effort and maintain consistency throughout your project.
Yes, MLflow integration tracks experiments and enables comparison across runs. This Skill sets up MLflow automatically within your Jupyter environment, logging parameters, metrics, and artifacts to maintain reproducibility and organize your experimental history for data science projects.
Phase-based planning breaks a 10-week FYP into structured phases with daily decision frameworks and weekly milestones. This Skill provides a timeline mapping activities across setup, data cleaning, EDA, modeling, and validation, helping you know what to prioritize each week.
Yes, the workflow covers the complete pipeline: preprocessing, exploratory data analysis, feature engineering, modeling, and validation. Each phase includes templates and guidance tailored to FYP requirements, with decision frameworks for applying specific methods.
Yes, this Skill connects with other skills like statistical validators and domain-specific FYP tools for end-to-end automation. The modular design enables you to extend the core workflow with specialized components while maintaining MLflow tracking and phase-based structure.
The Skill handles environment setup automatically within Jupyter, configuring MLflow tracking and initializing templates. You need a Jupyter environment; the Skill provides ready-made components for scripts and references that work with standard data science libraries.
KaranKathur06Clean tabular datasets by imputing missing values, removing duplicates, detecting outliers, and standardizing data types.
EmaRimoldiAnalyze ML experiment artifacts with descriptive and inferential statistics to generate analysis reports.
thbraetAssess trained models beyond aggregate metrics for CRISP-DM workflows.
emilneuraz-aiAutomate end-to-end MLOps pipelines from data preparation to deployment.
