Calculates self-correlation and PPAC (Power Pool Alpha Correlation) for WorldQuant BRAIN alphas Locally, this can be very fast than query the platform via mcp. Use this when the user calculates alpha correlations, checks PPAC.
Automatically analyzes BRAIN dataset fields and generates feature engineering ideas for alpha creation. Input: data category, delay, region parameters; Output: markdown document with deep feature engineering suggestions. The skill performs autonomous analysis based on dataset and field information, proposing meaningful feature concepts.
Provides 6 proven methods to evaluate new datasets on the WorldQuant BRAIN platform. Includes methods for checking coverage, non-zero values, update frequency, bounds, central tendency, and distribution. Use when the user wants to understand a specific datafield (e.g., "what is this field?", "how often does it update?").
Provides a comprehensive workflow for deep-diving into entire WorldQuant BRAIN datasets. Includes steps for dataset selection, field categorization, detailed description generation, and cross-platform research. Use when the user wants to "audit a dataset", "categorize fields", or "explore a new dataset".
Provides a step-by-step workflow for analyzing and explaining WorldQuant BRAIN alpha expressions. Use this when the user asks to explain a specific alpha expression, what a datafield does, or how operators work together. Includes steps for data field lookup, operator analysis, and external research.
Implements WorldQuant Brain features from an idea markdown file. Downloads dataset and generates alpha expressions defined in the idea.
Provides detailed requirements, thresholds, and improvement tips for WorldQuant BRAIN Alpha submission tests. Covers Fitness, Sharpe, Turnover, Weight, Sub-universe, and Self-Correlation tests. Use this when the user asks about alpha submission failures, how to improve alpha metrics, or test requirements.
Provides a systematic 5-step workflow for improving WorldQuant BRAIN alphas. Includes steps for gathering alpha info, evaluating datafields, proposing idea-focused improvements (using arXiv), simulating variants, and validating. Use when the user wants to improve an existing alpha or fix failing submission tests.