alphaear-predictor — Claude Code skill: market forecasts with Kronos
This skill produces a Kronos-based forecast for a financial time series, then adjusts the numbers against fresh news. Useful when you need a short-horizon price view.
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a claude-codeWhat alphaear-predictor does
Two stages. First scripts/kronos_predictor.py runs through KronosPredictorUtility and returns a quantitative base forecast from historical data. Then the agent picks up the forecast adjustment prompt in references/PROMPTS.md and shifts the numbers by hand to match recent news and market logic.
You need the Kronos model and an embedding model. Put trained weights in exports/models at the project root, named so they match the kronos_news_*.pt pattern; the base model downloads on its own. The embedding path comes from EMBEDDING_MODEL, which defaults to sentence-transformers/all-MiniLM-L6-v2, and KRONOS_MODEL_PATH overrides model loading.
Weights load with weights_only=True, and the skill scans only for the kronos_news_*.pt mask. Anything else dropped into that folder is worth checking before you run it. Dependencies are torch, transformers, sentence-transformers, pandas, numpy and scikit-learn.
What it helps with
- forecast a price series 7 days out from historical data
- adjust a quantitative forecast for breaking news
- return KLine points for downstream analysis
- compare the raw model forecast with the agent-adjusted version
Example prompts for the agent
- Forecast 600519 for the next 7 days with alphaear-predictor
- Generate the base forecast and adjust it against the latest news
- Run KronosPredictorUtility on this ticker and show me the KLine points
How to install alphaear-predictor
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a claude-code2Manually: put the files in place
~/.claude/skills/alphaear-predictor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/alphaear-predictor/
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a codex2Manually: put the files in place
.agents/skills/alphaear-predictor/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a cursor2Manually: put the files in place
.cursor/skills/alphaear-predictor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install RKiding/Awesome-finance-skills alphaear-predictor2Manually: put the files in place
.github/skills/alphaear-predictor/SKILL.md1Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a gemini-cli2Platform CLI
gemini skills install https://github.com/RKiding/Awesome-finance-skills --path skills/alphaear-predictorManually: put the files in place
.devin/skills/alphaear-predictor/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about alphaear-predictor
How do I install alphaear-predictor in Claude?
Run npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a claude-code. The skill file then lands at ~/.claude/skills/alphaear-predictor/SKILL.md.
What does alphaear-predictor do?
It forecasts a financial time series with the Kronos model, then the agent adjusts those numbers based on news sentiment.
What do I need before running it?
The Kronos model and an embedding model. Place weights in exports/models and set the embedding path through EMBEDDING_MODEL.
Source text
SKILL.md · Apache-2.0
---
name: alphaear-predictor
description: Market prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments.
---
# 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
### 1. Forecast Market Trends
**Workflow:**
1. **Generate Base Forecast**: Use `scripts/kronos_predictor.py` (via `KronosPredictorUtility`) to generate the technical/quantitative forecast.
2. **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):**
```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)
```
## Configuration
This skill requires the **Kronos** model and an embedding model.
1. **Kronos Model**:
- Ensure `exports/models` directory exists in the project root.
- Place trained news projector weights (e.g., `kronos_news_v1.pt`) in `exports/models/`.
- Or depend on the base model (automatically downloaded).
> [!CAUTION]
> **Model Security**: This skill loads model weights from `exports/models`. We use `weights_only=True` and only scan for the `kronos_news_*.pt` pattern. Ensure you only place trusted checkpoints in this directory.
2. **Environment Variables**:
- `EMBEDDING_MODEL`: Path or name of the embedding model (default: `sentence-transformers/all-MiniLM-L6-v2`).
- `KRONOS_MODEL_PATH`: Optional path to override model loading.
## Dependencies
- `torch`
- `transformers`
- `sentence-transformers`
- `pandas`
- `numpy`
- `scikit-learn`
© RKiding · Apache-2.0 · RKiding/Awesome-finance-skills
