Alphaear Sentiment

This one's for analyzing sentiment in financial text, which is trickier than general sentiment because "restructuring" or "volatility" hit differently in markets. You get two modes: FinBERT running locally for speed when you're batch processing news headlines, or you can have the LLM do it when you need actual reasoning about why something's bullish or bearish. Returns a score from negative one to positive one plus a label and explanation. The batch processing method is handy if you're maintaining a news database and need to catch up on sentiment scores. Straightforward tool if you're building anything that needs to gauge market mood from text.

skills.sh installs: 649
GitHub stars: 3.1K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

AlphaEar Sentiment Skill

Overview

This skill provides sentiment analysis capabilities tailored for financial texts, supporting both FinBERT (local model) and LLM-based analysis modes.

Capabilities

1. Analyze Sentiment (FinBERT / Local)

Use scripts/sentiment_tools.py for high-speed, local sentiment analysis using FinBERT.

Key Methods:

analyze_sentiment(text): Get sentiment score and label using localized FinBERT model.
- Returns: {'score': float, 'label': str, 'reason': str}.
- Score Range: -1.0 (Negative) to 1.0 (Positive).
batch_update_news_sentiment(source, limit): Batch process unanalyzed news in the database (FinBERT only).

2. Analyze Sentiment (LLM / Agentic)

For higher accuracy or reasoning capabilities, YOU (the Agent) should perform the analysis using the Prompt below, calling the LLM directly, and then update the database if necessary.