Skill UI

This skill generates a structured, non-advisory worksheet for planning trade ideas, basket adjustments, or comparing prediction markets. It helps users methodically review venues, underliers, constraints, and manual execution steps without placing any trades or providing financial advice. Ideal for the research phase of quantitative finance workflows.

This tool scans ingested OHLCV market data to automatically detect and classify various candlestick patterns, such as dojis, engulfing patterns, and head-shoulders formations. It not only identifies the pattern name but also assigns a type (reversal/continuation), direction, and a quantitative reliability score. It is an essential utility for technical analysis, helping users identify potential market turning points or continued trends.

This skill dispatches computationally intensive quantitative trading jobs (such as multi-year walk-forward analysis, large Monte-Carlo simulations, parameter sweeping, or deep model training) to a managed cloud agent runtime. It is designed for large-scale, production-grade backtesting that exceeds local machine capacity, ensuring robust execution and artifact management via Anthropic's cloud services.

A comprehensive tool for training and evaluating advanced neural network models (including LSTM, Transformer, and N-BEATS) on time-series market data. It facilitates the prediction of financial trends, generating results with confidence intervals, and comparing performance across multiple architectures. Ideal for quantitative trading research and financial forecasting.

This plugin provides advanced vector search capabilities using two distinct paths. The large-scale path supports millions of vectors via HNSW, ideal for general corpus search. The hot-path router handles small, critical pattern routing (≤11 patterns) with sub-ms latency. Key features include RaBitQ 1-bit quantization for memory efficiency (32× reduction), hyperbolic space search for hierarchical data, and unified cross-namespace search.

This tool generates a detailed, local 'receipt' or impact report of all Claude Code activity recorded in local session transcripts. It cross-references this data with your local Git history to provide a quantifiable measure of effort and project contribution. Ideal for performance reviews, budget justifications, or self-auditing usage.

This dashboard provides a comprehensive, single-view operational picture of campaign health. It monitors active campaigns by showing real-time health scores, logging auto-corrections (e.g., bid adjustments, budget reallocation), displaying current guardrail rules, and identifying campaigns needing human attention. It quantifies the estimated savings achieved through automated optimizations, helping users trust the automated system while focusing strategic effort on critical issues.

A comprehensive tool for monitoring and tracking brand visibility across major generative AI engines (ChatGPT, Gemini, Perplexity, etc.). It provides a quantitative framework to score brand presence, track changes over time, and identify optimization opportunities for emerging Generative Engine Optimization (GEO).

Transforms complex raw campaign data and performance metrics into a cohesive, executive-level QBR presentation. This tool structures performance retrospectives, identifies root causes for underperformance, quantifies ROI, and develops data-backed strategic recommendations for the next quarter. Ideal for client reviews, leadership updates, and strategic planning sessions.

Utilize Monte Carlo simulation to model complex marketing scenarios and predict revenue outcomes with quantified probability distributions. This tool is essential for assessing downside risk, understanding potential upside, and validating the probability of hitting specific revenue targets when testing budget shifts, channel mix changes, or new campaign launches.

A comprehensive guide outlining rigorous data analysis and reporting standards for geographic manuscripts. It covers spatial statistics, remote sensing accuracy, and qualitative interpretation, emphasizing spatial honesty, quantifying uncertainty, and ensuring results are robust across different scales and units.

A comprehensive guide for strengthening the methodological design of advanced geographical manuscripts. It covers various paradigms including spatial/quantitative GIScience, remote sensing, qualitative human geography, and mixed methods. Key advice areas include rigorously addressing spatial dependence (MAUP), validating measurements, justifying case selection, and ensuring holistic integration of diverse data sources.