Agent skill · data analytics · rkiding
alphaear-sentiment
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.
Why this skill is useful
Adds specific methods for sentiment analysis of financial texts using FinBERT and LLM, which are not commonly available in generic models.
What it needs
Requires torch, transformers installed locally. About 1k tokens when loaded. Last updated 2026-03-29. 2,757 stars on the source repository.
What this skill does
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 Capabilities 1. Analyze Sentiment (FinBERT / Local) Use scripts/sentimenttools.py for high-speed, local sentiment analysis using FinBERT. Key Methods: analyzesentiment(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). batchupdatenewssentiment(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. Sentiment Analysis Prompt Use this prompt to analyze financial texts if the local tool is insufficient or if reasoning is required. Scoring Guide: Positive (0.1 to 1.0): Optimistic news, profit growth, policy support, etc. Negative (-1.0 to -0.1): Losses, sanctions, price drops, pessimism. Neutral (-0.1 to 0.1): Factual reporting, sideways movement, ambiguous impact. Helper Methods updatesinglenewssentiment(id, score, reason): Use this to save your manual analysis to the database. Dependencies torch (for FinBERT) transformers (for FinBERT) sqlite3 (built-in) Ensure DatabaseManager is initialized correctly.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills rkiding/alphaear-sentiment