3. Data, Science & AI

Provides AI-powered music recommendations by analyzing YouTube Music playlists and user preferences to suggest similar artists, songs, and new music discoveries.

Implements comprehensive data validation rules across database, application, and pipeline layers to ensure data integrity and quality.

Comprehensive guide to implementing data lakehouse architecture with Delta Lake, Iceberg, and Hudi for unified data processing and analytics.

Provides LLM observability for Vercel AI SDK, enabling analytics, usage tracking, token cost monitoring, and performance observation of AI applications.

Expert data annotation service for machine learning, handling labeling workflows and quality assurance to prepare high-quality training datasets.

Provides programmatic access to analytics data via REST API for querying, dashboard building, and backend integration.

Analyzes statistical distributions to support data analysis and hypothesis testing, enabling evidence-based decision making.

Orchestrates multi-agent systems, enabling agent coordination, task delegation, and workflow management for AI agent networks.

Comprehensive guide for evaluating Retrieval-Augmented Generation systems, covering retrieval metrics, generation quality, and end-to-end frameworks.

Defines data contracts specifying schema, quality standards, and SLAs for seamless data exchange between producers and consumers.

Detects, measures, and reduces algorithmic bias in AI models to ensure equitable outcomes and ethical deployment.

References the main Data Validation Rules skill for implementing comprehensive data quality checks and validation logic.

Configures automated machine learning pipelines for hyperparameter optimization and model selection.

Provides structured playbooks and procedures for resolving data quality issues, data loss, corruption, and pipeline failures in data systems.

Manages identification, assessment, and mitigation of risks in machine learning model deployment and business process integration.

Monitors data freshness and latency, providing SLO tracking to ensure data pipelines meet reliability targets.

Provides an active learning system for ML with human-in-the-loop, utilizing uncertainty sampling and optimizing annotation workflows for efficient labeling.

Checklist to identify and remove redundant content in AI prompts, context, and responses, reducing token costs and improving signal-to-noise ratio.

Comprehensive guide to ELT modeling patterns, dimensional modeling, and data warehouse design including fact and dimension tables.

Provides executive dashboards for visualizing KPIs, business intelligence insights, and generating performance reports.

Provides categorical encoding techniques for ML feature engineering, including one-hot, target encoding, and embeddings.

Expert A/B testing framework for statistical experiments and machine learning model optimization.

Configures Airbyte for ETL/ELT data pipelines, connectors, and data synchronization.

Builds and optimizes SQL window functions for analytical queries, including OVER clauses and ranking functions.