3. Data, Science & AI

Guidelines for CRUD operations on seed files, including sequence reset, file structure, naming conventions, and testing methods for initial data management.

Intelligently routes user requests to the most appropriate AI agent based on request context and agent capabilities.

Summarizes per-model usage and cost data for Codex and Claude from CodexBar CLI, providing current model details or full breakdowns.

Provides best practices for using the Oracle CLI, including prompt handling, file bundling, engine selection, session management, and file attachment patterns for efficient AI interactions.

Selects optimal AI agents for tasks by evaluating capabilities, permissions, and workflow dependencies in multi-agent systems.

Executes statistical calculations on JSON data records using the JSONata query language for data analysis.

Generates high-quality images using Black Forest Labs' FLUX models for advanced AI-powered visual content creation.

Expert in building and optimizing data lake infrastructure for DB and Excel sources, ensuring efficient query performance and data management.

Converts PDF, Word, HTML, and other documents to Markdown for efficient LLM processing and text analysis.

Analyzes complex user intentions and orchestrates multi-agent collaboration for efficient AI system operation.

AI-powered tool for replacing, editing, or regenerating specific regions within images.

Processes arbitrarily long documents, codebases, and datasets exceeding LLM context windows using Recursive Language Model (RLM) for multi-hop reasoning and large-scale analysis.

Seeds test data into PapayaPOS database for various testing scenarios including chart data, database resets, and user mappings.

Measures factual accuracy, completeness, and consistency of AI systems with defined performance thresholds.

Plans complex architectural issues through AI debate between Claude and Codex models using multi-round analysis.

Enables enterprise AI system coordination through multi-agent patterns on Oracle Cloud Infrastructure.

Evaluates stock investment potential using financial ratios, earnings data, and social media sentiment analysis.

Guides SQLite database management, schema migrations, and changes for the Memory Hub project.

Defines the core personality and operational guidelines for the AI's behavior and thinking patterns.

Guidelines for building robust ETL processes with idempotence, quality gates, and CSV/XLSX import handling for data pipelines.

Provides expert database design and optimization for relational databases, including schema planning, indexing, sharding, and multi-tenant isolation strategies.

Creates agent definition files specifying capabilities, tools, and integration points for LLM-based AI agents.

Provides Supabase-recommended best practices for optimizing PostgreSQL performance, including query tuning, schema design, and configuration.

Analyzes user spending patterns and financial data via LunchMoney API, providing insights on budgets, subscriptions, and recurring expenses for specified time periods.