# Send Nautilus Trader to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "nautilus-trader", "name": "Nautilus Trader", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ahuserious/nautilus-trader", "canonicalUrl": "https://clawhub.ai/ahuserious/nautilus-trader", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/nautilus-trader", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nautilus-trader", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/CHANGELOG.md", "references/README.md", "references/api.md", "references/backtesting.md", "references/concepts.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/nautilus-trader" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/nautilus-trader", "downloadUrl": "https://openagent3.xyz/downloads/nautilus-trader", "agentUrl": "https://openagent3.xyz/skills/nautilus-trader/agent", "manifestUrl": "https://openagent3.xyz/skills/nautilus-trader/agent.json", "briefUrl": "https://openagent3.xyz/skills/nautilus-trader/agent.md" } } ``` ## Documentation ### Nautilus Trader Skill Comprehensive assistance with NautilusTrader development. Includes complete Hyperliquid mainnet integration with SDK patch for live trading. ### Overview This skill covers: Strategy development with NautilusTrader Backtesting using the Parquet data catalog Live trading deployment on Hyperliquid mainnet SDK patch for Hyperliquid price precision requirements ### When to Use Building trading strategies with NautilusTrader Running backtests with historical data Deploying strategies to Hyperliquid mainnet Debugging NautilusTrader adapter issues Working with multi-timeframe (MTF) indicators ### Core Dependencies # NautilusTrader (backtesting + live trading framework) pip install nautilus_trader # Hyperliquid SDK (for live trading patch) pip install hyperliquid-python-sdk eth-account python-dotenv # Data handling pip install pandas numpy ### Verify Installation import nautilus_trader print(f"Nautilus Trader: {nautilus_trader.__version__}") # Tested with v1.222.0 ### Environment Variables Create a .env file for Hyperliquid credentials: HYPERLIQUID_PK=your_private_key_without_0x_prefix HYPERLIQUID_VAULT=0xYourVaultAddressHere ### 1. Apply the Hyperliquid Patch (for live trading) # CRITICAL: Import patch BEFORE Nautilus Trader import hyperliquid_patch # Then import Nautilus normally from nautilus_trader.adapters.hyperliquid import HYPERLIQUID from nautilus_trader.live.node import TradingNode ### 2. Basic Strategy Template from nautilus_trader.trading.strategy import Strategy from nautilus_trader.config import StrategyConfig from nautilus_trader.model.data import Bar, BarType from nautilus_trader.model.enums import OrderSide, TimeInForce from nautilus_trader.model.identifiers import InstrumentId from decimal import Decimal class MyStrategyConfig(StrategyConfig): instrument_id: str bar_type: str trade_size: Decimal = Decimal("0.1") class MyStrategy(Strategy): def __init__(self, config: MyStrategyConfig): super().__init__(config) self.instrument_id = InstrumentId.from_str(config.instrument_id) self.bar_type = BarType.from_str(config.bar_type) self.trade_size = config.trade_size def on_start(self): self.instrument = self.cache.instrument(self.instrument_id) self.subscribe_bars(self.bar_type) def on_bar(self, bar: Bar): # Your strategy logic here pass def on_stop(self): self.close_all_positions(self.instrument_id) ### Heiken Ashi Indicator from nautilus_trader.indicators.base.indicator import Indicator from nautilus_trader.model.data import Bar class HeikenAshi(Indicator): """Heiken Ashi candle smoothing indicator.""" def __init__(self): super().__init__([]) self.ha_open = 0.0 self.ha_close = 0.0 self.ha_high = 0.0 self.ha_low = 0.0 self._prev_ha_open = None self._prev_ha_close = None self.initialized = False def handle_bar(self, bar: Bar) -> None: o, h, l, c = float(bar.open), float(bar.high), float(bar.low), float(bar.close) self.ha_close = (o + h + l + c) / 4 if self._prev_ha_open is None: self.ha_open = (o + c) / 2 else: self.ha_open = (self._prev_ha_open + self._prev_ha_close) / 2 self.ha_high = max(h, self.ha_open, self.ha_close) self.ha_low = min(l, self.ha_open, self.ha_close) self._prev_ha_open = self.ha_open self._prev_ha_close = self.ha_close self.initialized = True @property def is_bullish(self) -> bool: return self.ha_close > self.ha_open @property def is_bearish(self) -> bool: return self.ha_close < self.ha_open def reset(self) -> None: self._prev_ha_open = None self._prev_ha_close = None self.initialized = False ### Multi-Timeframe EMA Strategy See references/hyperliquid.md for complete MTF EMA + Heiken Ashi strategy implementation. Key concepts: HTF (Higher Timeframe): Determines trend direction via EMA crossover LTF (Lower Timeframe): Entry timing via Heiken Ashi confirmation Entry: HA color change in trend direction Exit: HA color reversal ### Engine Setup from nautilus_trader.backtest.engine import BacktestEngine, BacktestEngineConfig from nautilus_trader.model.currencies import USD from nautilus_trader.model.enums import AccountType, OmsType from nautilus_trader.model.identifiers import Venue from nautilus_trader.model.objects import Money from nautilus_trader.persistence.catalog import ParquetDataCatalog from decimal import Decimal def run_backtest(): config = BacktestEngineConfig( trader_id="BACKTESTER-001", logging_level="INFO", ) engine = BacktestEngine(config=config) # Add venue engine.add_venue( venue=Venue("HYPERLIQUID"), oms_type=OmsType.NETTING, account_type=AccountType.MARGIN, base_currency=USD, starting_balances=[Money(100_000, USD)], ) # Load data from catalog catalog = ParquetDataCatalog("./data_catalog") instruments = catalog.instruments() for instrument in instruments: engine.add_instrument(instrument) bars = catalog.bars() engine.add_data(bars) # Add strategy strategy = MyStrategy(config=MyStrategyConfig( instrument_id="SOL-USD.HYPERLIQUID", bar_type="SOL-USD.HYPERLIQUID-5-MINUTE-LAST-EXTERNAL", trade_size=Decimal("1.0"), )) engine.add_strategy(strategy) # Run engine.run() # Results print(engine.trader.generate_account_report(Venue("HYPERLIQUID"))) print(engine.trader.generate_order_fills_report()) print(engine.trader.generate_positions_report()) engine.dispose() ### Data Catalog See references/backtesting.md and references/data.md for detailed catalog operations: ParquetDataCatalog - Query and manage Parquet data files BarDataWrangler - Convert pandas DataFrames to Nautilus Bar objects write_data() - Persist data to catalog query() - Retrieve data with time filters ### Node Configuration import os from dotenv import load_dotenv load_dotenv() # CRITICAL: Apply patch BEFORE Nautilus imports import hyperliquid_patch from nautilus_trader.adapters.hyperliquid import ( HYPERLIQUID, HyperliquidDataClientConfig, HyperliquidExecClientConfig, ) from nautilus_trader.live.node import TradingNode, TradingNodeConfig from nautilus_trader.config import LiveDataEngineConfig, LiveExecEngineConfig def main(): node_config = TradingNodeConfig( trader_id="LIVE-001", data_engine=LiveDataEngineConfig(), exec_engine=LiveExecEngineConfig(), ) node = TradingNode(config=node_config) data_config = HyperliquidDataClientConfig( wallet_address=os.getenv("HYPERLIQUID_VAULT"), is_testnet=False, ) exec_config = HyperliquidExecClientConfig( wallet_address=os.getenv("HYPERLIQUID_VAULT"), private_key=os.getenv("HYPERLIQUID_PK"), is_testnet=False, ) node.build() # Add your strategy strategy = MyStrategy(config=my_config) node.trader.add_strategy(strategy) node.run() if __name__ == "__main__": main() ### Set Leverage (One-Time Setup) from hyperliquid.exchange import Exchange from hyperliquid.utils import constants from eth_account import Account import os private_key = os.getenv("HYPERLIQUID_PK") if not private_key.startswith("0x"): private_key = "0x" + private_key account = Account.from_key(private_key) exchange = Exchange(account, constants.MAINNET_API_URL) # Set 10x leverage for SOL (cross margin) exchange.update_leverage(10, "SOL", is_cross=True) ### Network Latency For best performance, deploy on AWS ap-northeast-1 (Tokyo): Ping to Hyperliquid CloudFront: ~1ms API latency: ~28ms ### The Problem Nautilus Trader v1.222.0 has bugs in the Hyperliquid adapter: Rust HTTP client serialization causes type mismatches Price precision exceeds Hyperliquid's 5 significant figure limit ### The Solution Bypass the buggy adapter using the official Hyperliquid Python SDK. The patch file is located at references/hyperliquid_patch.py. ### Price Precision Rules Hyperliquid requires maximum 5 significant figures for all prices: PriceValid?Sig Figs$139.05Yes5$139.054No6$1.2345Yes5$1.23456No6$12345Yes5$123456No6 ### Usage # CRITICAL: Import patch BEFORE any Nautilus imports import hyperliquid_patch # Then import Nautilus normally from nautilus_trader.adapters.hyperliquid import HYPERLIQUID The patch auto-applies on import and handles: Price formatting to 5 significant figures Rounding up for buys, down for sells (ensures fills) SDK-based order submission bypassing Rust client ### Verified Working Tested on Hyperliquid Mainnet 2025-01-12: SELL 0.72 SOL @ $143.38 - FILLED BUY 0.71 SOL @ $143.39 - FILLED ### File Structure your_trading_project/ ├── .env # Credentials (gitignored) ├── hyperliquid_patch.py # SDK patch for live trading ├── heiken_ashi.py # Heiken Ashi indicator ├── my_strategy.py # Strategy implementation ├── backtest.py # Backtest runner ├── live.py # Live trading runner └── data_catalog/ # Parquet data for backtesting ### Bar Type Format {symbol}.{venue}-{step}-{aggregation}-{price_type}-{source} Examples: SOL-USD.HYPERLIQUID-1-HOUR-LAST-EXTERNAL SOL-USD.HYPERLIQUID-5-MINUTE-LAST-EXTERNAL BTC-USD.HYPERLIQUID-15-MINUTE-LAST-EXTERNAL ### Order Rejected: Invalid Price Ensure prices have max 5 significant figures. Use the format_price_5_sigfigs() function from the patch. ### Connection Error Check .env has correct HYPERLIQUID_PK and HYPERLIQUID_VAULT Verify private key format (with or without 0x prefix) Confirm vault address is correct ### Patch Not Applied Ensure import hyperliquid_patch comes BEFORE any Nautilus imports. ### Missing Data in Backtest Verify data catalog path exists Check instrument IDs match between data and strategy config Ensure bar types are correctly formatted ### Position Not Closing Check that reduce_only=True is set on exit orders for netting accounts. ### Reference Files Detailed documentation is available in references/: FileDescriptionhyperliquid.mdComplete Hyperliquid integration guidehyperliquid_patch.pySDK patch source codestrategies.mdStrategy patterns and examplesbacktesting.mdData catalog and backtest APIdata.mdData handling and wranglinggetting_started.mdNautilusTrader fundamentalsconcepts.mdCore concepts and architectureapi.mdFull API reference Use view to read specific reference files when detailed information is needed. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ahuserious - Version: 0.1.0 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-30T16:55:25.780Z - Expires at: 2026-05-07T16:55:25.780Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/nautilus-trader) - [Send to Agent page](https://openagent3.xyz/skills/nautilus-trader/agent) - [JSON manifest](https://openagent3.xyz/skills/nautilus-trader/agent.json) - [Markdown brief](https://openagent3.xyz/skills/nautilus-trader/agent.md) - [Download page](https://openagent3.xyz/downloads/nautilus-trader)