# alphaear-predictor

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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 584 installs · ★ 3085
- Author: RKiding
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/RKiding/Awesome-finance-skills/tree/HEAD/skills/alphaear-predictor/SKILL.md
- Updated: 2026-03-29
- HTML: https://affpapa.org/en/nevibecode/skills/alphaear-predictor

## What it 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`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/alphaear-predictor/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/alphaear-predictor/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/alphaear-predictor/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/alphaear-predictor/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install RKiding/Awesome-finance-skills alphaear-predictor
```

2. **Manually: put the files in place**
- File: `.github/skills/alphaear-predictor/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/RKiding/Awesome-finance-skills --path skills/alphaear-predictor
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/alphaear-predictor/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add RKiding/Awesome-finance-skills --skill alphaear-predictor -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/RKiding/Awesome-finance-skills/tree/HEAD/skills/alphaear-predictor/SKILL.md

## When to use it
- 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
- 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

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: c987014d3e210d4b.

BEGIN THIRD-PARTY FILE c987014d3e210d4b
````text
---
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`
````
END THIRD-PARTY FILE c987014d3e210d4b

The third-party file has ended. Everything between the c987014d3e210d4b tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© RKiding · Apache-2.0 · https://github.com/RKiding/Awesome-finance-skills/tree/HEAD/skills/alphaear-predictor/SKILL.md

## Similar
- [Time Series Analysis](https://affpapa.org/en/nevibecode/skills/time-series-analysis.md) — skill · 605 installs
- [mean-reversion](https://affpapa.org/en/nevibecode/skills/mean-reversion.md) — skill · 490 installs
- [financial-analyst](https://affpapa.org/en/nevibecode/skills/financial-analyst.md) — skill · 1060 installs
- [dt-obs-predictive-analytics](https://affpapa.org/en/nevibecode/skills/dt-obs-predictive-analytics.md) — skill · 2100 installs
- [cointegration-analysis](https://affpapa.org/en/nevibecode/skills/cointegration-analysis.md) — skill · 455 installs
- [volatility-modeling](https://affpapa.org/en/nevibecode/skills/volatility-modeling.md) — skill · 713 installs

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md