- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add RKiding/Awesome-finance-skills --skill alphaear-sentiment -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add RKiding/Awesome-finance-skills --skill alphaear-sentiment -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add RKiding/Awesome-finance-skills --skill alphaear-sentiment -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add RKiding/Awesome-finance-skills --skill alphaear-sentiment -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/RKiding/Awesome-finance-skills/tree/HEAD/skills/alphaear-sentiment來自發布者
This skill provides sentiment analysis capabilities tailored for financial texts, supporting both FinBERT (local model) and LLM-based analysis modes.
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.
{'score': float, 'label': str, 'reason': str}.batch_update_news_sentiment(source, limit): Batch process unanalyzed news in the database (FinBERT only).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.
Use this prompt to analyze financial texts if the local tool is insufficient or if reasoning is required.
请分析以下金融/新闻文本的情绪极性。
返回严格的 JSON 格式:
{"score": <float: -1.0到1.0>, "label": "<positive/negative/neutral>", "reason": "<简短理由>"}
文本: {text}
Scoring Guide:
update_single_news_sentiment(id, score, reason): Use this to save your manual analysis to the database.torch (for FinBERT)transformers (for FinBERT)sqlite3 (built-in)Ensure DatabaseManager is initialized correctly.
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.
---name: alphaear-sentimentdescription: Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment…---# skills/alphaear-sentiment/SKILL.md常見問題
從發布者下載 skills/alphaear-sentiment/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/RKiding/Awesome-finance-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。