메뉴
Creates a custom indicator class in QuantConnect/LEAN. Invoke for "create a custom indicator", "implement [name] indicator", "I need an indicator LEAN doesn't have", "PythonIndicator", "custom indicator class". Skip for LEAN built-ins (SMA, EMA, RSI).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when subscribing to a QuantConnect/LEAN alternative-data class via `AddData<AltClass>(symbol)` and reading the result from `slice` in `OnData`. Triggers — "is this dataset a list or single point per bar", "why does iterating slice[dataset_symbol] fail", "why does .property error on a Quiver/RegAlytics/EODHDEconomicEvents value", missing-attribute errors after `slice[_datasetSymbol]`. Skip when — the dataset is a universe (use alternative-data-universes), Morningstar fundamentals, ETF constituents, or the price feed comes through `AddEquity` / `AddOption` instead of `AddData`.
Use when adding a custom or external data source to a QuantConnect/LEAN algorithm. Triggers: custom data reader, external dataset, `BaseData`, CSV, JSON, XML, ZIP, REST endpoint, Object Store, linked data, unlinked signals, custom universes, or local files for a QC strategy. Skip existing QC datasets subscribed with `AddData`, unless writing a custom reader.
Use when subscribing to a QuantConnect/LEAN alternative-data class via `add_data(<AltClass>, symbol)` and reading the result from `slice` in `on_data`. Triggers — "is this dataset a list or single point per bar", "why does iterating slice[dataset_symbol] fail", "why does .property error on a Quiver/RegAlytics/EODHDEconomicEvents value", missing-attribute errors after `slice[dataset_symbol]`. Skip when — the dataset is a universe (use alternative-data-universes), Morningstar fundamentals, ETF constituents, or the price feed comes through `add_equity` / `add_option` instead of `add_data`.
Use when adding a custom or external data source to a QuantConnect/LEAN algorithm. Triggers: custom data reader, external dataset, `PythonData`, CSV, JSON, XML, ZIP, REST endpoint, Object Store, linked data, unlinked signals, custom universes, or local files for a QC strategy. Skip existing QC datasets subscribed with `add_data`, unless writing a custom reader.
Use when subscribing to a QuantConnect/LEAN alternative-data class via py`add_data(<AltClass>, symbol)`cs`AddData<AltClass>(symbol)` and reading the result from py`slice`cs`slice` in py`on_data`cs`OnData`. Triggers — "is this dataset a list or single point per bar", "why does iterating slice[dataset_symbol] fail", "why does .property error on a Quiver/RegAlytics/EODHDEconomicEvents value", missing-attribute errors after py`slice[dataset_symbol]`cs`slice[_datasetSymbol]`. Skip when — the dataset is a universe (use alternative-data-universes), Morningstar fundamentals, ETF constituents, or the price feed comes through py`add_equity`cs`AddEquity` / py`add_option`cs`AddOption` instead of py`add_data`cs`AddData`.
Use when writing, reviewing, or refactoring QuantConnect/LEAN algorithm code for style correctness. Triggers: new algorithm code, code review, cleanup, "fix code style", "review code quality", "clean up the algorithm", redundant imports, subscription variable usage, comment format, blank-line rules, multi-line boolean layout, or catch-all error handling. Skip when only debugging runtime behavior or performance, unless the fix also changes style.
| name | custom-indicator |
| description | Creates a custom indicator class in QuantConnect/LEAN. Invoke for "create a custom indicator", "implement [name] indicator", "I need an indicator LEAN doesn't have", "PythonIndicator", "custom indicator class". Skip for LEAN built-ins (SMA, EMA, RSI). |
Creates a custom indicator class and wires it into an algorithm.
Ask the user: (1) indicator name; (2) formula/logic; (3) input type -- IndicatorDataPoint (single price), TradeBar (OHLCV, default), QuoteBar (bid/ask); (4) period; (5) internal LEAN indicators (SMA, EMA, RSI) -- construct and update inside ComputeNextValue; (6) scope -- single symbol or universe; (7) warm-up -- manual (recommended) or automatic.
Python: from AlgorithmImports import * only. Inherit PythonIndicator. File: snake_case.py in its own file.
C#: inherit Indicator (or BarIndicator for OHLCV). Set WarmUpPeriod in constructor. File: PascalCase.cs.
Manual warm-up (default): loop History<TradeBar>(symbol, period + 1, Resolution.Daily), call indicator.Update(bar) before RegisterIndicator.
Automatic warm-up: Settings.AutomaticIndicatorWarmUp = true in Initialize.
public class CustomVolatility : Indicator
{
private readonly RollingWindow<decimal> _window;
public CustomVolatility(int period) : base("CustomVolatility")
{
_window = new RollingWindow<decimal>(period);
WarmUpPeriod = period;
}
public override bool IsReady => _window.IsReady;
protected override decimal ComputeNextValue(IndicatorDataPoint input)
{
_window.Add(input.Value);
if (!IsReady) return 0m;
// Compute from _window here.
return 0m;
}
}
For OHLCV in C#, inherit BarIndicator and use IBaseDataBar in ComputeNextValue.
var symbol = AddEquity("SPY", Resolution.Daily).Symbol;
_indicator = new CustomVolatility(period);
foreach (var bar in History<TradeBar>(symbol, period + 1, Resolution.Daily))
_indicator.Update(bar);
RegisterIndicator(symbol, _indicator);
C# mirrors Python: use OnSecuritiesChanged, RegisterIndicator, DeregisterIndicator, Liquidate. Gate reads on _indicators[symbol].IsReady.
quantconnect:create_file with the indicator class.quantconnect:update_file_contents for main.py / Main.cs.from custom_volatility import CustomVolatility after from AlgorithmImports import *.quantconnect:create_compile. Poll quantconnect:read_compile until BuildSuccess or BuildError. Fix errors and loop.quantconnect:create_backtest. Poll quantconnect:read_backtest until complete.IsReady becomes true and at least one order placed (if the algorithm has entry conditions).