npx skills add javajack/skill-algotrader

cd ~/.claude/skills
git clone https://github.com/javajack/skill-algotrader.git algotrader
cd algotrader
./start.sh wizard  # Start using the skill

export CLAUDE_SKILLS_PATH=~/work/skills
cd ~/work/skills
git clone https://github.com/javajack/skill-algotrader.git algotrader
cd algotrader
./start.sh wizard

cd ~/.claude/skills/algotrader  # or your custom path
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Or use the convenience script (auto-creates venv)
./start.sh wizard

$ /algotrader

╔══════════════════════════════════════════════════════════════╗
║              ALGOTRADER BOT GENERATION WIZARD                ║
╚══════════════════════════════════════════════════════════════╝

Scanning current directory for trading code...
✓ Found: backtest.py, signal_generator.py

What would you like to do?
  1. Generate new trading bot from scratch
  2. Enhance existing code (fix issues, optimize)
  3. Create universe JSON from live index data
  4. Run backtest comparison
  5. Analyze performance

> 1

Let's design your trading bot. I'll ask a few questions...

/algotrader universe

Fetching live index data from NSE...
✓ Nifty 50: 50 stocks (updated: 2026-02-14)
✓ Nifty 100: 100 stocks
✓ Nifty Midcap 150: 150 stocks
✓ Nifty Smallcap 250: 250 stocks

Created:
  └─ universe/
     ├─ nifty50.json (50 stocks, ₹500Cr+ mcap)
     ├─ nifty100.json (100 stocks)
     ├─ midcap150.json (150 stocks, ₹50-500Cr mcap)
     └─ smallcap250.json (250 stocks, ₹10-50Cr mcap)

Each file includes:
  - Symbol, company name, ISIN
  - Market cap, sector
  - Liquidity metrics (avg volume, spread)
  - Last updated timestamp

🔥 CRITICAL: Tick Size Rounding
Mistake: kite.place_order(price=1847.35, ...)
Error: "Tick size for this script is 5.00"
Fix: price = round(price / tick_size) * tick_size  # 1847.35 → 1850.00
Impact: 90% of order rejections are tick size errors

🔥 CRITICAL: VWAP Must Reset Daily
Mistake: Cumulative VWAP across days
Symptom: Backtest 65% win rate, live 40%
Fix: Reset at market open (9:15)
Impact: #1 cause of backtest-live parity violations

# Create .env file (never commit this!)
cat > .env << EOF
KITE_API_KEY=your_api_key
KITE_API_SECRET=your_api_secret
KITE_ACCESS_TOKEN=your_access_token
EOF

# Launch wizard
/algotrader

# Or directly in Claude Code chat
> /algotrader wizard

trading_bot/
├── config.json          # Strategy parameters
├── main.py             # Entry point
├── signal_generator.py # Signal logic
├── data_manager.py     # Data fetching and caching
├── risk_manager.py     # Position sizing, Kelly Criterion
├── zerodha_client.py   # API integration
└── universe/
    └── nifty50.json    # Stock universe (fetched from NSE)

/algotrader universe --indices nifty50,nifty100,midcap150

# Creates JSON files with latest constituents
# Includes liquidity filtering, market cap, sector

# Point to your existing trading code
/algotrader check ./my_trading_bot.py

# Output:
⚠️  Found 3 issues:
1. Tick size not rounded (line 45) - will cause order rejections
2. VWAP not reset daily (line 89) - backtest-live parity violation
3. No symbol cooldown (line 120) - risk of revenge trading

Recommended fixes:
  1. Add tick_size rounding: price = round_to_tick(price, symbol)
  2. Reset VWAP at 9:15: if is_new_day(): vwap_state.reset()
  3. Add 45min cooldown: if not can_trade_symbol(symbol): return None

Apply fixes automatically? (y/n):

from algotrader import generate_fortress_signal

# Your OHLCV data with indicators
df = load_data("RELIANCE", date="2026-02-14")

signal = generate_fortress_signal(
    df=df,
    symbol="RELIANCE",
    config={
        'rsi_long_min': 45,
        'rsi_long_max': 65,
        'adx_min': 25,
        'volume_mult': 1.5
    }
)

if signal:
    print(f"🎯 LONG signal for {signal['symbol']}")
    print(f"   Entry: ₹{signal['entry_price']}")
    print(f"   Stop Loss: ₹{signal['stop_loss']}")
    print(f"   Target: ₹{signal['target']}")
    print(f"   Confidence: {signal['confidence']:.0%}")
    print(f"   Reason: {signal['reason']}")

from algotrader import compare_backtests

# Compare backtest results with live trading
comparison = compare_backtests(
    backtest_file="backtests/fortress_v2.parquet",
    live_file="backtests/live_results.parquet"
)

print(f"Win Rate: {comparison['backtest_winrate']:.1%} → {comparison['live_winrate']:.1%}")
print(f"Delta: {comparison['winrate_delta']:.1%}")

if comparison['parity_issues']:
    print("\n⚠️  Parity Issues:")
    for issue in comparison['parity_issues']:
        print(f"  - {issue['description']}")
        print(f"    Fix: {issue['recommended_fix']}")

from algotrader.universe import fetch_index_constituents, filter_universe

# Fetch latest Nifty 50 from NSE
nifty50 = fetch_index_constituents("NIFTY 50")
print(f"✓ Fetched {len(nifty50)} stocks")

# Apply liquidity filtering
filtered = filter_universe(
    nifty50,
    min_volume=100_000,      # Min daily volume
    max_spread_pct=0.3,      # Max bid-ask spread
    min_atr_pct=0.15,        # Min volatility
    max_atr_pct=2.5          # Max volatility
)

print(f"✓ After filtering: {len(filtered)} stocks")

# Save to JSON
save_universe(filtered, "universe/nifty50_filtered.json")

algotrader/
├── skill.json              # Skill manifest (Claude Code integration)
├── README.md              # This file
├── KNOWLEDGE.md           # All 16 domains (1,780 lines of learnings)
├── NUANCES.md             # 30+ token-burning gotchas
├── algotrader.py          # Main CLI + wizard (~800 lines)
├── requirements.txt       # Python dependencies
├── templates/
│   ├── minimal_intraday.py    # Bare minimum intraday bot (50 lines)
│   └── minimal_positional.py  # Bare minimum positional bot (50 lines)
└── examples/
    ├── full_system.py         # Complete reference implementation (~300 lines)
    └── universe_fetcher.py    # Fetch index constituents from NSE

from algotrader.risk import detect_market_regime, calculate_position_size

# Detect regime (BULL, BEAR, SIDEWAYS)
regime = detect_market_regime(nifty_data)

# Adjust position size
base_size = 500_000  # ₹5L base
regime_multipliers = {
    "BULL": 1.2,      # +20% in bull market
    "BEAR": 0.5,      # -50% in bear market
    "SIDEWAYS": 0.8   # -20% in sideways
}

position_size = base_size * regime_multipliers[regime]
# BULL: ₹6L, BEAR: ₹2.5L, SIDEWAYS: ₹4L

from algotrader.risk import calculate_kelly_position

kelly = calculate_kelly_position(
    win_rate=0.65,     # 65% win rate
    avg_win=0.012,     # 1.2% avg win
    avg_loss=0.006     # 0.6% avg loss
)

print(f"Full Kelly: {kelly['full_kelly']:.1%}")      # 28.6%
print(f"Half Kelly: {kelly['half_kelly']:.1%}")      # 14.3% (recommended)
print(f"Use {kelly['recommended']:.1%} of capital")

from algotrader.analytics import generate_daily_report

report = generate_daily_report(trades_file="logs/trades.jsonl")

print(f"📊 Daily Performance:")
print(f"   Trades: {report['total_trades']}")
print(f"   Win Rate: {report['win_rate']:.1%}")
print(f"   P&L: ₹{report['pnl']:,.0f}")
print(f"   Best Trade: {report['best_trade']['symbol']} (+{report['best_trade']['pnl_pct']:.1%})")
print(f"   Worst Trade: {report['worst_trade']['symbol']} ({report['worst_trade']['pnl_pct']:.1%})")
print(f"   Sharpe Ratio: {report['sharpe_ratio']:.2f}")

# Fix: Round to tick size
from algotrader.zerodha import get_tick_size, round_to_tick

tick_size = get_tick_size("RELIANCE")  # 0.05
price = round_to_tick(1847.35, tick_size)  # 1847.35 → 1847.35 (already ok)
price = round_to_tick(1847.33, tick_size)  # 1847.33 → 1847.35

# Likely causes:
1. VWAP not reset daily - check if VWAP resets at 9:15
2. Candle completion not checked - add 500ms buffer
3. Different data sources - use same cache for both
4. Slippage not modeled - add realistic slippage (₹2-5)

# Run parity diagnostic:
/algotrader backtest compare backtest.parquet live.parquet

# Fix: Add symbol cooldown
symbol_cooldowns[symbol] = time.time()
if time.time() - symbol_cooldowns.get(symbol, 0) < 45*60:
    return None  # Skip signal for 45 minutes