quant-ml-trading

Complete quantitative and ML-powered trading toolkit — strategy validation, genetic optimization, decay monitoring, reinforcement learning, signal aggregation, data science pipelines, and statistical/quant foundations. Use this skill for: "generate a backtest report", "create tearsheet", "equity curve", "Monte Carlo simulation", "strategy report", "performance tearsheet", "backtest results", "drawdown analysis", "strategy statistics", "risk report", "publish backtest", "PDF report", "HTML report", "walk-forward", "out of sample validation", "rolling optimization", "WFO", "anchored walk forward", "parameter stability", "robustness test", "rolling backtest", "adaptive optimization", "parameter reoptimization", "stress test", "bootstrap simulation", "worst case scenario", "parameter sensitivity", "confidence interval", "ruin probability", "survival analysis", "tail risk", "heatmap", "parameter sweep", "optimization surface", "3D surface", "parameter landscape", "which parameters matter", "robust parameters", "se

설치로 이동

저장소: mahmoud20138/Tradecraft
최근 소스 활동: 2026년 4월 23일 08:40
감지된 SKILL.md 언어: 영어
스타: 15
포크: 4

설치 방법

기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.

npx skills add https://github.com/mahmoud20138/Tradecraft --skill quant-ml-trading

명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.

로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.

소스 파일 검토

설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.

SKILL.md

소스 지침 · 읽기 전용 미리보기

name: quant-ml-trading
description: Complete quantitative and ML-powered trading toolkit — strategy validation, genetic optimization, decay monitoring, reinforcement learning, signal aggregation, data science pipelines, and statistical/quant foundations. Use this skill for: "generate a backtest report", "create tearsheet", "equity curve", "Monte Carlo simulation", "strategy report", "performance tearsheet", "backtest results", "drawdown analysis", "strategy statistics", "risk report", "publish backtest", "PDF report", "HTML report", "walk-forward", "out of sample validation", "rolling optimization", "WFO", "anchored walk forward", "parameter stability", "robustness test", "rolling backtest", "adaptive optimization", "parameter reoptimization", "stress test", "bootstrap simulation", "worst case scenario", "parameter sensitivity", "confidence interval", "ruin probability", "survival analysis", "tail risk", "heatmap", "parameter sweep", "optimization surface", "3D surface", "parameter landscape", "which parameters matter", "robust parameters", "sensitivity analysis", "parameter grid search", "A/B test strategies", "compare strategies", "which strategy is better", "statistical comparison", "strategy comparison", "head to head", "variant testing", "significance test", "optimize strategy", "evolve parameters", "genetic algorithm", "breed strategies", "parameter optimization", "auto-optimize", "find best parameters", "evolutionary search", "mutation", "crossover", "fitness function", "population-based optimization", "is my strategy still working", "strategy decay", "alpha decay", "edge erosion", "performance degradation", "parameter drift", "when to retire a strategy", "strategy health check", "is the edge gone", "strategy monitoring", "live vs backtest divergence", "reinforcement learning trading", "RL agent", "deep Q-network trading", "PPO trading", "train an agent", "learn from replay", "reward function trading", "AI agent that learns to trade", "gym trading environment", "state space market", "action space trading", "combine all signals", "aggregate strategies", "meta strategy", "AI signal", "ensemble signal", "which signal to follow", "best signal now", "combine everything", "master signal", "AI recommendation", "backtesting framework", "walk-forward analysis", "overfitting prevention", "survivorship bias", "look-ahead bias", "performance metrics", "Sharpe", "Sortino", "Calmar", "Information Ratio", "win rate", "profit factor", "expectancy", "R-multiple", "SQN", "ARIMA models", "GARCH volatility", "regression analysis", "Fama-French factors", "machine learning trading", "random forest", "XGBoost", "LSTM", "feature engineering for trading", "market regime detection", "NLP sentiment analysis", "algorithmic execution", "TWAP", "VWAP", "implementation shortfall", "factor investing", "value", "momentum", "size", "quality", "low volatility", "statistical arbitrage", "cointegration", "mean reversion statistics", "Z-score trading", "analyze trading data", "build ML models on price data", "feature engineering on market data", "store retrieve analysis results", "run data science on my pairs", "find patterns in the data", "statistical analysis of EURUSD", "cluster market regimes", "anomaly detection on price", "store my analysis", "retrieve past analysis", "data pipeline", "machine learning on forex data", "train a model", "feature importance", "large-scale data processing", "ETL", "persistent result storage", "data science pipeline", "data cleaning", "data validation", "OHLCV cleaning", or any strategy validation, genetic optimization, decay detection, RL trading, ML signal aggregation, quantitative analysis, or data science task applied to trading.
related_skills: ["ml-trading","backtesting-sim","statistics-timeseries","backtesting-sim"]
tags: ["trading","quant","machine-learning","genetic","reinforcement-learning","signals"]
skill_level: expert
kind: reference
category: trading/quant
status: active

> **Skill:** Quant Ml Trading | **Domain:** trading | **Category:** quantitative | **Level:** expert > **Tags:** `trading`, `quant`, `machine-learning`, `genetic`, `reinforcement-learning`, `signals` # Quant & ML Trading — Complete Toolkit ## Overview Five powerful tools for quantitative strategy work: 1. **Strategy Validation** — backtest tearsheets, walk-forward OOS, Monte Carlo, sensitivity, A/B testing 2. **Genetic Optimizer** — evolve strategy parameters using evolutionary algorithms 3. **Decay Monitor** — detect when a live strategy is losing its edge 4. **RL Trade Agent** — reinforcement learning agent (DQN) that learns to trade from market replay 5. **AI Signal Aggregator** — combine signals from all strategies using weighted voting + ML meta-model ## Reference Files | File | Contents | |------|----------| | `references/strategy-validation.md` | Tearsheet, walk-forward WFO, Monte Carlo, sensitivity heatmaps, A/B testing | | `references/genetic-optimizer.md` | Gene encoding, fitness functions, GA engine, anti-overfitting safeguards | | `references/tensortrade-rl.md` | Strategy decay monitor (CUSUM, rolling Sharpe, live vs backtest) + RL trading environment + DQN agent | | `references/ai-signal-aggregator.md` | Weighted voting, ML meta-learner, confidence calibration, trade decision engine | | `references/quantitative-trading.md` | Quant workflow diagram, performance metrics table, pitfalls table, key formulas (Sharpe/Kelly/Z-score/IR/Expectancy) | | `references/statistics-timeseries.md` | Descriptive stats, return distributions, stationarity (ADF/KPSS), ARIMA models, GARCH volatility, regression, Fama-French factors, cointegration | | `references/ml-trading.md` | Supervised learning (XGBoost/LSTM/RF configs), feature engineering, regime detection (K-Means/HMM/GMM), RL, NLP sentiment, model validation | | `references/backtesting-execution.md` | 10 backtesting rules, walk-forward, Monte Carlo, detailed performance metrics, 8 pitfalls, TWAP/VWAP/IS execution, factor strategies | | `references/data-science-pipeline.md` | DataPipeline (OHLCV clean/validate/resample), FeatureEngine, StatisticalAnalysis, ModelFactory, TradingDataStore (persistent storage) | ## Quick Decision Guide ``` Strategy tearsheet / backtest report / Monte Carlo? → Load references/strategy-validation.md Parameter optimization / genetic algorithm / evolve strategy? → Load references/genetic-optimizer.md Strategy decay / live vs backtest divergence / RL agent? → Load references/tensortrade-rl.md Combine signals / meta-model / AI signal aggregation? → Load references/ai-signal-aggregator.md Quant workflow / performance metrics / key formulas? → Load references/quantitative-trading.md Stats / time series / ARIMA / GARCH / regression / Fama-French? → Load references/statistics-timeseries.md ML models / feature engineering / regime detection / NLP? → Load references/ml-trading.md Backtesting rules / execution algos / factor strategies (detail)? → Load references/backtesting-execution.md Data cleaning / feature pipeline / anomaly detection / persistent storage / ETL? → Load references/data-science-pipeline.md Multiple topics? → Load all relevant reference files ``` ## Anti-Overfitting Rules (ALL skills) 1. Always use walk-forward OOS — never optimize on all available data 2. Monte Carlo bootstrap required before any live deployment 3. GA/RL results MUST be validated on unseen temporal data 4. Meta-model must be re-trained monthly with rolling walk-forward 5. Live vs backtest Sharpe gap > 0.5 = pause the strategy immediately --- --- ## Related Skills - [Ai Pattern Recognition](../ml-trading.md) - [Backtesting Sim](../backtesting-sim.md) - [Statistical Analysis](../statistics-timeseries.md) - [Algorithmic Strategies](../backtesting-sim.md)

GitHub에서 보기

검색으로 돌아가기 설치로 돌아가기

markets

Entry-point live-market scan. Returns current quote, H1/H4 regime, session state, and watch levels for a default watchlist (gold, US30, US500, US100, EURUSD, GBPUSD, BTCUSD, ETHUSD) — or any custom list. Uses the free yfinance path by default, MT5 if available. USE FOR - scan markets, what's moving, market overview, current prices, what's on the watchlist, show me the markets.

2026-04-23

recommendations

Entry-point ranked-setup feed. Runs the full pair-analyze pipeline against a watchlist and returns the top N highest-grade trade setups right now, sorted by confidence × R:R, with one-line rationale and a copy-pasteable trade plan. USE FOR - what should I trade, recommend trades, best setups, top picks, ranked opportunities, where's the edge.

2026-04-23

Entry-point skill discovery. Given a keyword or task description, returns the shortest list of Tradecraft skills that match, with direct invocation recipes. No keyword = show the 5 main entry points. USE FOR - find skill, which skill, how do I, search skills, list skills, what can this do, find command.

2026-04-23

이 저장소의 모든 Skills 보기

quant-ml-trading

소스 정보

설치 방법

소스 파일 검토

이 저장소의 다른 Skills

이 저장소의 다른 Skills