Alphaear Predictor

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.

skills.sh installs: 588
GitHub stars: 3.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rkiding/awesome-finance-skills --skill alphaear-predictor --agent claude-code

Installs into .claude/skills of the current project.

Files

AlphaEar Predictor Skill

Overview

This skill utilizes the Kronos model (via KronosPredictorUtility) to perform time-series forecasting and adjust predictions based on news sentiment.

Capabilities

1. Forecast Market Trends

Workflow:

Generate Base Forecast: Use scripts/kronos_predictor.py (via KronosPredictorUtility) to generate the technical/quantitative forecast.
Adjust Forecast (Agentic): Use the Forecast Adjustment Prompt in references/PROMPTS.md to subjectively adjust the numbers based on latest news/logic.

Key Tools:

KronosPredictorUtility.get_base_forecast(df, lookback, pred_len, news_text): Returns List[KLinePoint].

Example Usage (Python):

from scripts.utils.kronos_predictor import KronosPredictorUtility
from scripts.utils.database_manager import DatabaseManager

db = DatabaseManager()
predictor = KronosPredictorUtility()

# Forecast
forecast = predictor.predict("600519", horizon="7d")
print(forecast)