3. Data, Science & AI

Manages relational and document databases including schema design, query optimization, and administration for PostgreSQL and MongoDB.

Optimizes context management for AI agents through token efficiency, memory systems, and multi-agent coordination to enhance LLM pipeline performance.

Comprehensive toolkit for web crawling, structured data extraction, and handling JavaScript-heavy pages to build automated data pipelines without LLMs.

Processes and generates multimedia content (audio, images, video, documents) via Google Gemini API for AI-powered analysis and creation.

Creates and validates LAMMPS input scripts with physics-based checks and educational feedback for molecular dynamics simulations.

Fetches real-time weather data from Open-Meteo API for application integration and analysis.

Analyzes investment research reports (PDF, image, Word) to extract stock data and generate structured investment strategy tables.

Provides HR-specific employee data query capabilities using an in-memory SQLite database, requiring no external dependencies.

Analyzes stock market data by fetching real-time information via Yahoo Finance API for trend identification and investment insights.

Enables AI-powered digital archiving with entity extraction, knowledge graph construction, and multi-source data integration for content management.

Enables data analysis, visualization, and statistical storytelling for news reporting and research using quantitative datasets.

Extracts website content with anti-bot bypass, paywall handling, and social media processing using Playwright and trafilatura.

Creates modular Python data pipelines for content processing, batch systems, and Google Sheets/Drive API integrations.

Queries Perplexity.ai via CLI for current information, research answers, and source-referenced explanations, outputting structured JSON for integration.

Loads CLAUDE.md context files from a vault to deliver comprehensive understanding of recent notes, vault structure, and current state for optimal AI session performance.

Extracts risk factors, MD&A, and business descriptions from SEC filings (10-K, 10-Q, 8-K) via Financial Datasets API.

Fetches real-time and historical stock and cryptocurrency prices from the Financial Datasets API for market tracking and analysis.

Retrieves and analyzes company financial data including revenue, earnings, margins, and valuations through a dedicated financial datasets API.

Provides a Gemini model spawner with event tracking for large-context research exploration and analysis.

Orchestrates multiple AI models (Codex, Gemini, Copilot, Claude) with spawner selection, cost optimization, and HeadlessSpawner patterns.

Enables creation, editing, and analysis of spreadsheets including formulas, formatting, and data visualization for structured data tasks.

Manages user preferences and learned knowledge with confidence scoring for reliable information retrieval.

Provides cost-first delegation patterns and decision frameworks for efficient multi-AI coordination and resource optimization.

Orchestrates multiple advanced LLMs for comprehensive research through peer review and synthesis, enhancing accuracy and depth.