skills.rest
qqlcx5
qqlcx5COMMUNITY
Explore all skills by this author →
WebsiteGitHub

quant-system-5steps

Runs a five-step crypto quant pipeline from data collection to backtested strategy output.

Updated Aug 15, 2026
Search Tags:#technical indicators#backtesting#crypto#strategy generation#binance#quantitative trading#lightgbm
One-click install
npx skills add https://github.com/qqlcx5/skills-hub --skill quant-system-5steps-qqlcx5
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: quant-system-5steps
Source: https://github.com/qqlcx5/skills-hub/tree/main/skills/quant-system-5steps
Command: npx skills add https://github.com/qqlcx5/skills-hub --skill quant-system-5steps-qqlcx5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, numpy, lightgbm.

What problem does it solve? Building a quantitative trading workflow normally requires wiring together data feeds, indicator calculations, ML model training, strategy selection, and backtesting by hand. This Skill automates that entire pipeline for crypto symbols in a single run. ## Core Features & Use Cases - Multi-source data collection: Fetches real-time prices and OHLCV history from Hyperliquid and Binance, with a synthetic-data fallback when live history is unavailable. - Indicator analysis and ML modeling: Computes 30+ technical indicators (MA, RSI, MACD, Bollinger, ATR) and trains a LightGBM classifier to produce LONG/SHORT signals with confidence scores. - Strategy generation and backtesting: Selects from 15+ strategy templates (momentum, mean reversion, supertrend, ichimoku, etc.) and reports win rate, total return, Sharpe ratio, and max drawdown. - Use Case: Ask the agent to analyze BTCUSDT; it collects market data, trains a model, picks a strategy template, and returns a full backtest report with optimization suggestions. ## Quick Start Run the five-step quant analysis on BTCUSDT and show me the signal, backtest metrics, and optimization suggestions.

Frequently Asked Questions about quant-system-5steps

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a quantitative trading backtest on BTCUSDT in Python?▼

Instantiate the QuantSystem5Steps class and call run("BTCUSDT"), or execute the script from the command line with the symbol as an argument. It collects data, trains a LightGBM model, selects a strategy template, and prints backtest metrics including win rate and Sharpe ratio.

What data sources does this quant pipeline use for crypto prices?▼

It fetches real-time prices from Hyperliquid and Binance, and historical OHLCV candles primarily from the Binance klines API. If live historical data is unavailable, it falls back to synthetic data generated from the current price.

Which trading strategy templates are included?▼

The pipeline includes 15+ templates such as momentum, mean reversion, breakout, MACD cross, supertrend, ichimoku, ADX trend, VWAP reversion, stochastic RSI, volume profile, CCI extreme, and Williams %R. A template is selected automatically based on current indicator conditions.

Does the backtest use real market history or synthetic data?▼

It uses real OHLCV history from Binance or Hyperliquid when available, but silently falls back to randomly generated synthetic candles if those APIs fail. You should verify the data source before trusting backtest metrics like Sharpe ratio or max drawdown.

What are the limitations of the LightGBM trading signal model?▼

The model trains on roughly 30 engineered features with a simple binary label for future price direction, so signals are research-grade rather than production trading advice. Results should be independently validated before any financial decision.

Related Skills

Explore More Data & Analytics Skills→
NigarumOvumNigarumOvum

okx-market

Retrieves real-time and historical crypto market data from OKX V5 REST API.

Community
Advanced
datagridSolutiondatagridSolution

AI Trading Studio

Convert natural-language trading goals into indicators, strategies, signals, and portfolio recommendations.

Official
Advanced
BankrBotBankrBot
80

Bankr Agent - Market Research

Retrieve token market data and technical indicators across multiple blockchains.

Official
Intermediate
agiprolabsagiprolabs
266

backtrader

Backtest trading strategies bar-by-bar with the backtrader Python framework.

Community
Advanced