AI skill for equity investors and traders. Automates systematic backtesting, market analysis, technical charting, economic calendar monitoring, and US stock research. Integrates with Claude and Python scripts.
git clone https://github.com/tradermonty/claude-trading-skills.gitClaude Trading Skills is an AI-powered automation tool designed for equity investors and traders who need to systematize their research and analysis workflows. The skill automates key trading activities including systematic backtesting of trading strategies, technical charting, economic calendar monitoring, and fundamental US stock research. It integrates with Claude Code and Python scripts to enable traders to execute complex analytical tasks programmatically. By combining Claude's reasoning capabilities with Python-based market analysis, the skill helps traders validate hypotheses, monitor economic indicators, and conduct technical analysis without manual repetition. This is particularly valuable for investors building trading systems that require consistent, data-driven decision-making.
1. **Customize the Prompt**: Replace all [PLACEHOLDERS] with your specific requirements (e.g., [STOCK_SYMBOL] = 'AAPL', [TIMEFRAME] = 'Weekly', [STRATEGY_NAME] = 'RSI Divergence'). For advanced users, modify the Python script in the technical analysis section to include custom indicators or timeframes. 2. **Run the Analysis**: Paste the customized prompt into Claude or ChatGPT. For Python-dependent tasks (backtesting, economic calendar integration), ensure you have the required libraries installed (e.g., `yfinance`, `backtesting`, `pandas`). Use this command in your terminal to install dependencies: ```bash pip install yfinance pandas backtesting python-dateutil requests ``` 3. **Review and Validate**: Cross-check the AI-generated technical levels with your own charting tools (e.g., TradingView, ThinkorSwim). For backtest results, verify the Python script logic matches your trading rules. Pay special attention to slippage assumptions and commission costs. 4. **Integrate with Sortd**: Use Sortd's kanban boards to track your trading plan execution. Create columns for 'Analysis', 'Watchlist', 'Positions', and 'Trades Executed'. Drag and drop emails (e.g., earnings alerts, Fed meeting minutes) into relevant columns to centralize your workflow. Enable Sortd's AI features to auto-tag emails by urgency or sentiment. 5. **Iterate and Improve**: After executing trades based on the report, log your results in Sortd. Use the 'Follow-up Management' template to track performance against the AI's predictions. Adjust your prompts based on what worked (e.g., refine economic calendar impact thresholds) and what didn't (e.g., modify backtest parameters).
Running systematic backtests on trading strategies across historical market data
Analyzing technical charts and identifying chart patterns for trade entry/exit signals
Monitoring economic calendar events and their potential market impact
Conducting fundamental research on US equities and company financial metrics
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/tradermonty/claude-trading-skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as a professional equity trader and automate systematic analysis for [STOCK_SYMBOL]. Generate a comprehensive trading report covering: 1) Technical analysis of [TIMEFRAME] price action with key support/resistance levels, 2) Backtest results for [STRATEGY_NAME] strategy over the past [PERIOD] with [METRICS] performance metrics, 3) Economic calendar events for the next [N_DAYS] days that could impact [STOCK_SYMBOL], 4) Fundamental screener results comparing [STOCK_SYMBOL] to its [PEER_GROUP] peers on [METRICS]. Use Python scripts where applicable and format the output with clear headers, tables, and actionable insights.
## Trading Analysis Report: NVIDIA Corporation (NVDA)
### Technical Analysis (Daily Chart - 6 Months)
NVIDIA's stock has shown remarkable strength in 2024, with a 45% YTD gain. The current price action reveals:
**Key Levels:**
- **Resistance:** $122.50 (all-time high from May 2024)
- **Support:** $108.75 (50-day moving average)
- **Breakout Target:** $135.00 (measured move from cup-and-handle pattern)
**Technical Indicators:**
- RSI (14): 68.2 (slightly overbought but within normal range)
- MACD: Bullish crossover on 6/15/2024 with histogram expansion
- Volume: 30-day average volume 42M shares, current session 58M (138% of avg)
### Strategy Backtest: Moving Average Crossover (50/200-day MA)
Backtested from 1/1/2020 to 6/30/2024 with $10,000 initial capital:
| Metric | Value | Comparison to Buy & Hold |
|----------------------|-------------|--------------------------|
| Total Return | +287.3% | +241.8% |
| Max Drawdown | -22.1% | -31.4% |
| Win Rate | 68.4% | 52.1% |
| Sharpe Ratio | 1.87 | 1.42 |
| Avg. Winning Trade | +8.2% | +6.8% |
**Python Code Used:**
```python
import yfinance as yf
import pandas as pd
from backtesting import Backtest, Strategy
# Fetch data
data = yf.download('NVDA', start='2020-01-01', end='2024-06-30')
# Define strategy
class MACrossover(Strategy):
n1 = 50
n2 = 200
def init(self):
close = self.data.Close
self.ma1 = self.I(SMA, close, self.n1)
self.ma2 = self.I(SMA, close, self.n2)
def next(self):
if crossover(self.ma1, self.ma2):
self.buy()
elif crossover(self.ma2, self.ma1):
self.position.close()
# Run backtest
bt = Backtest(data, MACrossover, cash=10000, commission=0.002)
stats = bt.run()
print(stats)
```
### Economic Calendar Impact (Next 7 Days)
| Date | Event | Expected Impact | Notes |
|------------|---------------------------|-----------------|--------------------------------|
| 7/8/2024 | FOMC Meeting Minutes | High | Potential Fed policy clues |
| 7/9/2024 | CPI Data Release | High | Inflation trend confirmation |
| 7/10/2024 | PPI Data Release | Medium | Producer price trends |
| 7/11/2024 | Earnings: TSLA | High | Semi-conductor sector catalyst |
| 7/12/2024 | Michigan Sentiment | Medium | Consumer confidence gauge |
**Trading Plan:**
- Pre-FOMC: Hold current positions, reduce size by 20%
- Post-CPI: Monitor for inflation surprise (expected: 3.1% YoY)
- Earnings week: Consider protective puts if volatility expected
### Fundamental Screener: NVDA vs. Semiconductor Peers
| Metric | NVDA | AMD | INTC | AVGO | QCOM |
|----------------------|-----------|----------|---------|---------|---------|
| P/E Ratio | 42.1x | 38.5x | 15.2x | 35.8x | 22.4x |
| PEG Ratio | 1.8 | 1.6 | 1.1 | 1.7 | 1.3 |
| Revenue Growth (YoY) | +61.4% | +37.2% | +5.8% | +45.1% | +12.3% |
| ROE | 34.2% | 22.1% | 11.5% | 28.7% | 24.5% |
| Debt/Equity | 0.12 | 0.08 | 0.45 | 0.05 | 0.18 |
**Key Insights:**
1. NVDA trades at a premium to peers (42.1x P/E vs. 26.8x peer average)
2. Exceptional revenue growth (61.4% YoY) justifies premium
3. Strongest ROE in sector (34.2%) indicates superior capital efficiency
4. Low debt levels provide flexibility for R&D and M&A
**Recommendation:** Maintain overweight position with 3% position size in portfolio. Consider adding on any pullback below $110 support level. Set stop-loss at $105 (9.5% below current price).Automate your browser workflows effortlessly
AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan