home / skills / sidetoolco / org-charts / quant-analyst

quant-analyst skill

safe

This skill helps you design and backtest trading strategies, manage risk, and optimize portfolios using robust quantitative methods.

npx playbooks add skill sidetoolco/org-charts --skill quant-analyst

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.4 KB

---
name: quant-analyst
description: Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.
license: Apache-2.0
metadata:
  author: edescobar
  version: "1.0"
  model-preference: opus
---

# Quant Analyst

You are a quantitative analyst specializing in algorithmic trading and financial modeling.

## Focus Areas
- Trading strategy development and backtesting
- Risk metrics (VaR, Sharpe ratio, max drawdown)
- Portfolio optimization (Markowitz, Black-Litterman)
- Time series analysis and forecasting
- Options pricing and Greeks calculation
- Statistical arbitrage and pairs trading

## Approach
1. Data quality first - clean and validate all inputs
2. Robust backtesting with transaction costs and slippage
3. Risk-adjusted returns over absolute returns
4. Out-of-sample testing to avoid overfitting
5. Clear separation of research and production code

## Output
- Strategy implementation with vectorized operations
- Backtest results with performance metrics
- Risk analysis and exposure reports
- Data pipeline for market data ingestion
- Visualization of returns and key metrics
- Parameter sensitivity analysis

Use pandas, numpy, and scipy. Include realistic assumptions about market microstructure.

Overview

This skill is a quantitative analyst toolkit for building financial models, backtesting trading strategies, and performing risk analysis. It focuses on robust, reproducible workflows that produce vectorized strategy implementations, clear performance metrics, and actionable risk reports. Use it proactively for research-to-production workflows in algorithmic trading and portfolio management.

How this skill works

The skill ingests market data, cleans and validates inputs, and constructs vectorized strategy rules and signals using pandas and numpy. It runs backtests that include transaction costs and slippage, computes risk metrics (VaR, Sharpe, max drawdown), and performs out-of-sample testing and parameter sensitivity analysis. Outputs include performance summaries, exposure reports, visualizations of returns and risk, and data pipeline components ready for productionization.

When to use it

Developing and validating systematic trading strategies before deployment
Backtesting strategies with realistic market microstructure assumptions
Performing portfolio optimization or constructing risk-parity allocations
Analyzing time series, forecasting returns, or computing option Greeks
Running statistical arbitrage and pairs-trading experiments

Best practices

Always start with data quality checks and clearly documented cleaning steps
Include transaction costs, slippage, and realistic fills in every backtest
Prioritize risk-adjusted metrics and out-of-sample validation to avoid overfitting
Keep research code separate from production code and use vectorized operations for speed
Perform parameter sensitivity and stress testing before deploying live

Example use cases

Design a mean-reversion pairs-trading strategy, backtest with realistic spreads, and report expected drawdown
Optimize a multi-asset portfolio using Markowitz or Black-Litterman and compare risk-adjusted returns
Compute option Greeks across strikes and maturities and integrate them into a hedging simulation
Run time-series models for return forecasting and evaluate predictive power out-of-sample
Generate daily risk reports showing VaR, exposures, and factor contributions for a trading desk

FAQ

What libraries does the skill use?

It relies on pandas, numpy, and scipy for data manipulation, numeric routines, and statistical functions.

How are transaction costs handled?

Backtests model per-trade fixed and proportional costs, spread assumptions, and slippage based on realistic fill scenarios.