3. Data, Science & AI

Optimizes AI agent context capacity to overcome limitations, reduce costs, and improve performance in long-running systems.

Transforms raw data into compelling narratives using visualization and persuasive structure for stakeholder presentations and reports.

Efficiently processes and transforms structured data using jq and yq for JSON, YAML, and TOML formats.

Processes incoming emails to extract sender data, identify communication intents, analyze sentiment, and update CRM records with AI insights.

Coordinates tasks across diverse AI providers and execution environments, enabling seamless delegation and integration of AI services.

Calculates portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown for risk assessment and monitoring.

Automates phylogenetic biogeographic analyses using BioGeoBEARS in R, handling data validation, reformatting, and visualization for ancestral range estimation.

Orchestrates tasks across multiple AI providers (Claude, OpenAI, Gemini, etc.) via capability-based routing and fallback strategies.

Analyzes data and generates professional visualizations using Python's pandas, matplotlib, and seaborn libraries.

Designs and implements multi-agent AI systems where agents coordinate through delegation, orchestration, and parallel processing to solve complex tasks.

Sandboxed Python execution for data analysis, visualization, and automated document generation (Excel, Word, PDF) with data cleaning and ML capabilities.

Autonomous AI framework for executing complex biomedical research tasks including genomics, drug discovery, and clinical analysis using LLM reasoning and integrated databases.

Professional D3.js data visualization tool for interactive charts, dashboards, and complex data displays.

Enables stateful AI agents with persistent memory patterns using AgentDB for session management, long-term storage, and context-aware interactions in chat systems and assistants.

Analyzes TopHub hot list data to identify trending topics and provide actionable content creation inspiration.

Validates Flyway database migration files for SQL syntax, version conflicts, and naming conventions to ensure data integrity.

Orchestrates multi-provider AI model interactions (Claude, Codex, Gemini, Cursor) using native task agents with terminal authentication fallback.

Core identity and command system for CodeConscious AI assistant, enabling cognitive operations via /runtime.* commands with constitutional governance and memory management.

Optimizes SQL queries, indexing, and caching to enhance database performance for PostgreSQL and MySQL.

Diagnoses machine learning training failures including loss divergence, gradient issues, and model architecture problems to resolve optimization challenges.

Creates charts, graphs, and visual reports from data for clear data representation and analysis.

Creates production-ready AI agents with optimized system prompts and domain-specific knowledge using Claude Agent SDK and evidence-based prompting techniques.

Open-source tool for web scraping and data processing with intelligent crawling, screenshots, and PDF export capabilities.

Provides step-by-step templates and guidance for creating AI agents in Unite-Hub, covering registration, testing, and governance.