This combines Kronos time series forecasting with news sentiment to predict market movements. You feed it stock data and recent news, and it generates a base technical forecast that you can then adjust using an agentic prompt based on sentiment analysis. The setup is straightforward if you already have the Kronos model weights in your exports directory, though note it expects a specific news projector checkpoint pattern. The two-step workflow (quantitative baseline, then news-aware adjustment) is sensible for financial forecasting where you want both technical signals and narrative context. Worth trying if you need market predictions that account for both price history and breaking news, though as always with ML market prediction, calibrate your expectations accordingly.
npx skills add https://github.com/rkiding/awesome-finance-skills --skill alphaear-predictor