菜单
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).
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/QuantConnect/Documentation --skill custom-indicator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
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 selecting a dynamic Equity universe from QuantConnect/LEAN alternative-data classes with `AddUniverse<AltClass>(selector)`. Covers Brain, CoinGecko, EODHD, Quiver Quantitative, and Smart Insider universes. Skip for Morningstar fundamentals, ETF constituents, or pure indicator-driven universes.
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`.
基于 SOC 职业分类
正在显示 SKILL.md
| 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 update; (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.
Manual warm-up (default): loop self.history[TradeBar](symbol, period + 1), call indicator.update(bar) before self.register_indicator.
Automatic warm-up: self.settings.automatic_indicator_warm_up = True in initialize.
class CustomVolatility(PythonIndicator):
def __init__(self, period):
super().__init__()
self.value = 0
self._window = RollingWindow[float](period)
def update(self, input_: BaseData):
self._window.add(input_.value)
if self._window.is_ready:
prices = np.array(list(self._window)[::-1])
self.value = np.std(np.diff(np.log(prices))) * math.sqrt(252) * 100
return self.is_ready
@property
def is_ready(self) -> bool:
return self._window.is_ready
def initialize(self):
symbol = self.add_equity("SPY", Resolution.DAILY).symbol
self._indicator = CustomVolatility(period)
for bar in self.history[TradeBar](symbol, period + 1):
self._indicator.update(bar)
self.register_indicator(symbol, self._indicator)
def on_securities_changed(self, changes):
for security in changes.added_securities:
security.indicator = CustomVolatility(period)
for bar in self.history[TradeBar](security, period + 1):
security.indicator.update(bar)
self.register_indicator(security, security.indicator)
for security in changes.removed_securities:
self.deregister_indicator(security.indicator)
self.liquidate(security)
quantconnect:create_file with the indicator class.quantconnect:update_file_contents for main.py.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.is_ready becomes true and at least one order placed (if the algorithm has entry conditions).