为什么值得关注

它明确划分职责：AI负责数据获取和用户交互，而所有技术指标由依赖零网络的确定性Python脚本计算，保证了可重复性和速度。三支柱评分系统与保护性措施（特殊持仓保护、强制确认）使其成为实用的短期投资管理工具。

适合谁使用

使用Claude Code并希望自动化技术分析的零售交易者
构建本地交易助手的量化开发者
遵循规则化方法管理短期投资组合的投资者

典型使用场景

使用三支柱评分卡分析股票或ETF的潜在买入或卖出时机
自动为跨资产市场环境进行每日宏观情绪评分
无需手动计算指标即可获得结构化交易建议（持有、退出、重新入场等）
作为Claude Code技能集成，实现对话式交易分析

项目优势

确定性计算：所有脚本仅使用Python标准库，执行速度快且无网络依赖
透明的三支柱框架（趋势、动能、宏观），评分范围-6至+6
强有力的保护措施：特殊持仓保护、账户隔离、T+1流动性检查、每笔订单需用户批准
易于集成：可作为技能放入Claude Code中交互使用

使用前须知

依赖Robinhood MCP获取数据，不兼容其他券商
宏观情绪需要手动从Investing.com注入10Y-2Y收益率利差，未完全自动化
未提供回测或历史表现验证

README 快速开始

Agentic Trading Desk

Personal trading desk for technical analysis and short-term portfolio management on stocks and ETFs. The system combines the automation and query capabilities of an Artificial Intelligence agent (via Robinhood MCP protocol) with local deterministic mathematical calculation engines in Python.

The ruling principle is: the AI fetches data and interacts with the user; the scripts perform the deterministic calculations; the user decides and approves execution.

🚀 Project Architecture

The project is designed to operate locally and modularly. All technical indicator computations are delegated to Python 3 scripts that only use the Python standard library (stdlib), ensuring speed and zero network dependencies during execution.

graph TD
    A[Robinhood MCP / API] -- Price Historicals / Quotes --> B[Claude / Agentic Core]
    C[Investing.com / Web] -- 10Y-2Y Spread / News --> B
    B -- JSON of Daily Closes --> D[scripts/macro_pillar.py]
    B -- JSON of Closes + Holding status --> E[scripts/score.py]
    D -- Injected Macro Score --> E
    E -- Raw Indicators --> F[scripts/indicators.py]
    E -- Three-Pillar Scorecard + Suggested Decision --> B
    B -- Visualized Proposal --> G[User]
    G -- Order Confirmation --> A

File Structure

SKILL.md: Operations manual and specific guardrails guiding the AI agent's actions.
scripts/indicators.py: Mathematical engine to calculate technical indicators without visual estimations.
scripts/macro_pillar.py: Macro regime detector and cross-asset sentiment scorer.
scripts/score.py: Evaluator of the three-pillar framework and exit/entry decision engine.

📈 The Three-Pillar Framework

Each analyzed asset is scored in three independent categories with scores from -2 to +2 (for a consolidated total range of -6 to +6):

1. Trend

Determined in scripts/score.py using:

Price position relative to the EMA 20.
Structural crossovers between exponential moving averages: EMA 20 > EMA 50 and EMA 50 > EMA 200.
Slope direction of the EMA 200 (measured relative to 5 bars ago).

2. Momentum

Determined in scripts/score.py combining:

RSI-14 using Wilder's smoothing (ne

项目描述

AI-assisted trading desk for short-term technical analysis on stocks & ETFs via Robinhood MCP. Deterministic Python engines score each asset on a three-pillar framework (Trend · Momentum · Macro-Sentiment) using EMA, RSI, MACD, TRIX & Bollinger Bands. The AI fetches data; the scripts compute; the human approves every order.

agentic-trading-desk