Data analysis, machine learning, LLM apps, and prompt design (9K skills)
Extract three to five plain-language trading rules from profitable trades, then test them across Chinese A-shares, Hong Kong stocks, US stocks, and crypto. Produce a report comparing simulated and actual results, with a breakdown of differences.
Finds and retrieves paid financial datasets when free sources lack coverage or detail. Guides comparison of providers, success rates, prices, and required inputs, while keeping execution costs and remaining credits visible.
Generate trading signals using Smart Money Concepts, a framework for interpreting institutional trading behavior. Analyze trend continuation, reversals, price gaps, and order concentration zones, then combine structural signals and gaps to determine a trading direction.
Plan portfolio allocations across assets using risk, correlations, return forecasts, and trading costs. Compare five optimization methods, produce settings for config.json, and define rebalancing rules that adjust holdings back toward their target weights.
Interpret crypto liquidation heatmaps, which show estimated price levels where leveraged positions may be forcibly closed. Organize major clusters, compare concentrations above and below the current price, and assess cascade risks and potential support or resistance zones.
Build machine-learning trading signals from price and volume data. The workflow checks inputs, creates predictive features, and repeatedly trains on available historical data to produce bounded signals indicating predicted direction and strength.
Explore bundled libraries of investment factors, signals used to compare securities, and inspect individual formulas and metadata. Evaluate a factor or an entire library across a chosen universe and period, producing aggregate performance statistics and an HTML report.
Compare yields from decentralized finance lending, liquidity provision, and staking. Assess returns alongside price-related losses, smart contract risks, and dependence on token rewards, then organize opportunities by risk and the sustainability of their income sources.
Research stock and cryptocurrency strategies through historical testing, factor analysis, and options pricing. Analyze trading journals, extract rules from profitable trades, and generate reports comparing simulated results with actual trading outcomes.
Analyze convertible bonds in China's A-share market through bond value, stock conversion value, and option value. Review conversion-price resets and redemption clauses, then compare candidates using low-price, low-premium screening and periodic portfolio rotation frameworks.
Analyze how assets move together and test cointegration, a long-term equilibrium relationship between prices. Find related assets, group similar holdings, examine changing correlations, and estimate hedge ratios and reversion times for pairs-trading research.
Use investor psychology to examine trading signals and risk controls, especially in China A-shares. The skill provides sentiment measures, checklists for biased decisions, and frameworks for assessing momentum, which follows trends, and reversal strategies.
Analyze crypto derivatives for research and backtesting using perpetual funding payments, futures prices across expiry dates, and options volatility. Organize market metrics, compare strategy candidates, and outline risks such as margin shortages, funding reversals, and exchange failures.
Retrieve stock prices, futures quotes, exchange rates, and economic indicators with the free Python library AKShare. The skill explains market-specific functions, symbol formats, and data preparation for analysis and testing strategies against historical data.
Analyze bid–ask spreads, order books, and buying and selling imbalances to assess liquidity, or how easily an asset trades. Estimate large-order price impact and transaction costs, with additional guidance on Chinese A-share auction and block trades.
Compare exchange-traded funds by fees, tracking accuracy, liquidity, and market-price differences from asset value. Use the China-focused framework and Python examples to screen products, examine sector rotation, and study portfolio allocation.
Track when assets begin moving together, assess the resulting loss of diversification, and examine which assets moved first during a crisis. Rank changes in asset relationships and report uncertainty explicitly for risk monitoring and retrospective analysis.
Evaluate investment factors across multiple securities using statistical measures and grouped backtests. Compare how well each factor predicts future returns, examine its consistency over time, and combine useful factors with equal or performance-based weights.
Organizes central bank policy, exchange rates, geopolitical risks, and capital flows into scored factors. Produces a structured macro report to support research into allocations across stocks, gold, and US Treasuries.
Use CCXT, a library with a common interface for over 100 cryptocurrency exchanges, to retrieve historical prices and volumes, current quotes, order books, and recent trades. Public market data requires no API key.
Choose financial data sources and tools for price history, financial statements, news, and economic research. The skill maps market coverage, credentials, access limits, and fallback options, and provides rules for checking important figures against independent sources.
Access stock fund flows, disclosures, news, financial statements, and market rankings through Vibe-Trading tools. The skill documents available data interfaces and examples, including symbol lookup, with market-specific sources and no token required.
Diagnose failed or abnormal backtests, which test trading strategies on historical data. Inspect result files, strategy code, and configuration to identify bugs, make targeted repairs, rerun tests, and verify the updated metrics.
Rewrite lengthy prompts, tool descriptions, and agent instructions into compact text while preserving requirements, exceptions, and exact values. The process records removed content and compares token counts, the units models use to measure text length.