3. Data, Science & AI

Guides users in managing databases with Navicat, including connection setup, SQL execution, and data administration tasks.

Guides integration of Alibaba Cloud AI services into Spring applications, covering model APIs and AI application development for Spring AI Alibaba.

Delivers expert guidance for Oracle database administration, SQL query writing, PL/SQL development, and Oracle-specific feature implementation.

Creates specialized subagents in Claude Code for delegated task execution and autonomous workflow management.

Generates raw SQL scripts for database schema modifications and data seeding, orchestrated via .NET Aspire.

Automates CSV cleaning by detecting encoding, inferring delimiters, and recovering malformed rows for reliable data processing.

Handles Parquet file patterns including partitioning, predicate pushdown, and schema evolution for efficient data storage and processing.

Orchestrates production ETL patterns, implementing reliability strategies and incremental data loading for efficient data pipelines.

Validates pandas DataFrames against predefined schemas with column checks and decorator-based rules for data integrity.

Optimizes content structure and framing for AI citation, enhancing trust, extractability, and fact-density to improve AI processing accuracy.

Provides pytest templates and patterns for testing ETL pipelines, covering unit, integration, and data quality checks.

Provides sales pipeline forecasting with weighted calculations, deal scoring models, and accuracy metrics for revenue prediction.

Provides a measurement framework for Answer Engine Optimization (AEO) with metrics including AI visibility, share of voice, citation monitoring, and referral demand.

Detects data anomalies using statistical methods (Z-score, IQR) and ML algorithms (Isolation Forest) for time-series and general data analysis.

Monitors data quality through scorecards, distribution tracking, and freshness checks for validation pipelines.

Provides dbt model organization patterns, incremental strategies, and testing best practices for data transformation workflows.

Generates statistical profiles for dataframes to enable exploratory data analysis and dataset understanding.

Provides incremental data loading patterns including CDC, backfill, and timestamp-based strategies for optimized data pipeline orchestration.

Provides data validation patterns, schema evolution tools, and test assertions for data pipeline development.

Generates synthetic test data with edge cases to validate ETL pipeline functionality and data transformations.

Enables data validation in pipelines with Great Expectations, featuring expectation suites, checkpoints, and data docs for monitoring.

Analyzes git history and session files to extract patterns and recommend development artifacts based on frequency thresholds.

Optimizes DataFrame operations through chunked processing, memory efficiency, and vectorized computations for large-scale data handling.

Guide for building custom AI agents with the Claude Agent SDK, covering setup, configuration, and TypeScript/Python code examples.