Data Engineering Data Driven Feature

What it does

This skill automates feature engineering pipelines from raw data using statistical analysis and machine learning techniques to improve model performance. It orchestrates a comprehensive data-driven development process, guiding you through phases of data analysis, hypothesis formulation, feature implementation, and post-launch analysis. Specialized agents are used in each phase to ensure features are built based on data insights and validated through experimentation.

When to use it

• When working on data-driven feature development tasks or workflows.
• When needing guidance, best practices, or checklists for data-driven feature development.
• For initial exploratory data analysis of user behavior data.
• To identify patterns, opportunities, and user segments based on existing data.

Key capabilities

• Data Analysis & Hypothesis Formation: Uses a "data-scientist" subagent to perform exploratory data analysis (EDA).
• Modern Analytics Tools Integration: Can leverage tools like Amplitude, Mixpanel, and Segment for understanding user journeys.
• Workflow Orchestration: Guides users through a structured process from initial data analysis to feature implementation and post-launch analysis.
• A/B Testing Support: Facilitates the validation of features through controlled experiments.

Example prompts

• "Perform exploratory data analysis for feature: [feature name]. Analyze existing user behavior data, identify patterns and opportunities."
• "Segment users by behavior and calculate baseline metrics for this new feature."
• "What are some potential areas for improvement based on current user journeys?"

Tips & gotchas

• Clearly define goals, constraints, and required inputs before using the skill.
• The resources/implementation-playbook.md file contains detailed examples and further instructions.
• This skill is specifically designed for data-driven feature development; it's not suitable for unrelated tasks or those requiring tools outside its scope.