Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/tools-only/X-Skills --skill openbb-equityThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
| name | openbb-equity |
| description | Comprehensive equity analysis using OpenBB - historical prices,... |
Perform comprehensive stock analysis using the OpenBB Platform.
/openbb-equity TICKER [--analysis fundamental|technical|all] [--period 1y]
Retrieves and analyzes equity data for any stock ticker using OpenBB's comprehensive data sources.
First, verify OpenBB is installed:
try:
from openbb import obb
print("✅ OpenBB installed")
except ImportError:
print("⚠️ Installing OpenBB...")
import subprocess
subprocess.run(["pip", "install", "openbb"], check=True)
from openbb import obb
# Parse user input
import sys
ticker = sys.argv[1].upper() if len(sys.argv) > 1 else "AAPL"
analysis_type = "all" # fundamental, technical, or all
period = "1y" # 1d, 1w, 1m, 3m, 6m, 1y, 5y
# Parse flags
for arg in sys.argv[2:]:
if arg.startswith("--analysis="):
analysis_type = arg.split("=")[1]
elif arg.startswith("--period="):
period = arg.split("=")[1]
# Get historical prices
price_data = obb.equity.price.historical(
symbol=ticker,
interval="1d",
period=period
)
df = price_data.to_dataframe()
print(f"\n📈 Historical Prices for {ticker}")
print(f"Period: {period}")
print(f"Latest Close: ${df['close'].iloc[-1]:.2f}")
print(f"52-Week High: ${df['high'].max():.2f}")
print(f"52-Week Low: ${df['low'].min():.2f}")
print(f"YTD Return: {((df['close'].iloc[-1] / df['close'].iloc[0]) - 1) * 100:.2f}%")
if analysis_type in ["fundamental", "all"]:
print(f"\n📊 Fundamental Analysis for {ticker}")
# Company profile
try:
profile = obb.equity.profile(symbol=ticker)
print(f"\nCompany: {profile.name}")
print(f"Sector: {profile.sector}")
print(f"Industry: {profile.industry}")
print(f"Market Cap: ${profile.market_cap / 1e9:.2f}B")
except:
print("Profile data not available")
# Financial metrics
try:
metrics = obb.equity.fundamental.metrics(symbol=ticker)
print(f"\nKey Metrics:")
print(f"P/E Ratio: {metrics.pe_ratio:.2f}")
print(f"EPS: ${metrics.eps:.2f}")
print(f"Dividend Yield: {metrics.dividend_yield:.2%}")
print(f"ROE: {metrics.roe:.2%}")
except:
print("Metrics data not available")
# Analyst ratings
:
ratings = obb.equity.estimates.analyst(symbol=ticker)
()
()
()
()
()
:
()
if analysis_type in ["technical", "all"]:
print(f"\n📉 Technical Analysis for {ticker}")
# Calculate technical indicators
import pandas as pd
# Simple Moving Averages
df['SMA_20'] = df['close'].rolling(window=20).mean()
df['SMA_50'] = df['close'].rolling(window=50).mean()
df['SMA_200'] = df['close'].rolling(window=200).mean()
current_price = df['close'].iloc[-1]
sma_20 = df['SMA_20'].iloc[-1]
sma_50 = df['SMA_50'].iloc[-1]
sma_200 = df['SMA_200'].iloc[-1]
print(f"\nMoving Averages:")
print(f"Current Price: ${current_price:.2f}")
print(f"SMA 20: ${sma_20:.2f} {'🟢' if current_price > sma_20 else '🔴'}")
print(f"SMA 50: ${sma_50:.2f} {'🟢' if current_price > sma_50 else '🔴'}")
()
delta = df[].diff()
gain = (delta.where(delta > , )).rolling(window=).mean()
loss = (-delta.where(delta < , )).rolling(window=).mean()
rs = gain / loss
df[] = - ( / ( + rs))
rsi = df[].iloc[-]
()
rsi > :
()
rsi < :
()
:
()
avg_volume = df[].rolling(window=).mean().iloc[-]
current_volume = df[].iloc[-]
()
()
()
()
Generate investment insights using Claude's analysis:
# Prepare summary for AI analysis
summary = {
"ticker": ticker,
"current_price": current_price,
"52w_high": df['high'].max(),
"52w_low": df['low'].min(),
"ytd_return": ((df['close'].iloc[-1] / df['close'].iloc[0]) - 1) * 100,
"technical": {
"sma_position": "bullish" if current_price > sma_200 else "bearish",
"rsi": rsi,
"volume_trend": "high" if current_volume > avg_volume else "normal"
}
}
print(f"\n🤖 AI Analysis for {ticker}:")
print("\nBased on the data above, here's my assessment:")
print(f"- Trend: {'Bullish' if current_price > sma_200 else 'Bearish'} (price {'above' if current_price > sma_200 else 'below'} 200-day SMA)")
print(f"- Momentum: {'Overbought' if rsi > 70 else rsi < } (RSI: )")
()
()
Create a formatted analysis report:
print(f"\n{'='*60}")
print(f"EQUITY ANALYSIS REPORT: {ticker}")
print(f"{'='*60}")
print(f"Generated: {pd.Timestamp.now().strftime('%Y-%m-%d %H:%M:%S')}")
print(f"Data Source: OpenBB Platform")
print(f"\nAnalysis Type: {analysis_type.upper()}")
print(f"Period Analyzed: {period}")
print(f"\n{'='*60}")
/openbb-equity AAPL
/openbb-equity TSLA --analysis=fundamental
/openbb-equity NVDA --analysis=technical --period=6m
/openbb-equity GOOGL --analysis=all --period=1y
# Compare with crypto
/openbb-crypto BTC --compare=equity
# Portfolio context
/openbb-portfolio --add=AAPL
# Macro correlation
/openbb-macro --impact=equity
pip install openbb)obb.user.credentials)
Based on SOC occupation classification