Skill UI

This comprehensive skill simulates an expert business analyst, specializing in transforming complex raw data into actionable, strategic insights. The scope covers modern Business Intelligence (BI) platforms (Tableau, Power BI), AI-powered predictive modeling, designing robust KPI/OKR frameworks, advanced financial modeling, and optimizing business processes. It is designed for users needing to drive data-driven decision-making and create executive-level reports.

This skill models the expertise of a senior data scientist, covering the entire data science lifecycle. It provides advanced capabilities in statistical modeling, machine learning (deep learning, XGBoost), predictive analytics, and business intelligence. From raw data exploration (EDA) to deploying production-ready models and creating actionable dashboards, it covers technical depth across Python, R, SQL, and cloud platforms, while applying domain knowledge in finance, marketing, and operations.

Monitors PostgreSQL and MySQL health with real-time metrics, predictive alerts, and automated remediation, letting you preempt bottlenecks and respond to production issues quickly.

Structured workflow for building hierarchical Bayesian models with PyMC 5+, covering data prep, NUTS sampling, diagnostics, posterior checks, and predictive inference.

A comprehensive tool for analyzing long-term health data, tracking trends across multiple dimensions such as weight, vital signs, symptoms, medication adherence, lab results, and mood. It identifies significant changes, correlations between lifestyle factors and health metrics, and provides data-driven insights, risk assessments, and predictive recommendations for proactive health management.

PyMC is a powerful Python library for probabilistic programming and advanced Bayesian inference. This comprehensive guide details the full workflow for building, fitting, and validating complex Bayesian models. Learn to implement hierarchical structures, perform MCMC sampling (NUTS), conduct posterior predictive checks (PPC), and effectively quantify uncertainty using industry best practices.

A comprehensive technical module covering foundational deep learning principles and cutting-edge computer vision architectures, drawing from Yann LeCun's research. Topics include CNN fundamentals, backpropagation theory, and advanced self-supervised learning (SSL) models such as SimCLR, MAE, and the modern Joint Embedding Predictive Architecture (JEPA). Provides detailed theoretical explanations and complete PyTorch code for implementation.

Soft Predict Future is a structured foresight engine that triggers whenever the user asks about future outcomes or scenarios. It enforces a nine-step analytical pipeline (validation, signal collection, scoring, driver extraction, etc.), highlights required searches and inputs, and directs the user to web-enabled reasoning for predictive analysis.

Build, fit, and validate Bayesian models with PyMC 6, covering hierarchical models, MCMC/NUTS sampling, variational inference, prior and posterior predictive checks, diagnostics, and LOO/WAIC model comparison.

A sophisticated system designed to automatically select the optimal AI agent and model tier (e.g., Haiku, Sonnet, Opus) for any non-trivial task. It replaces manual decision-making by integrating learned patterns, predictive modeling, and a robust 3-tier routing mechanism. The process is fully auditable, providing a detailed routing rationale to ensure transparency and reliable execution.

This comprehensive skill assists authors in evaluating the suitability and optimal framing of their computer science manuscript for the International Conference on Discovery Science. It provides deep, venue-specific guidance on required evidence, scope vocabulary (e.g., automated discovery, explainable patterns), and structural adjustments needed to emphasize the scientific discovery process, rather than just predictive results. Essential for optimizing high-level conference submission strategy.

This skill provides comprehensive guidance for submitting research to npj Computational Materials. It defines the journal's scope, requiring rigorous computational methods (DFT, MD, ML, high-throughput screening) that yield generalizable materials insights or predictive capabilities. It educates authors on the required standards, including methodological rigor, reproducibility, and adherence to FAIR data principles, helping authors re-frame their work for a high-impact venue.