- Home
- Skills
- Trading & Investing
- Quantitative Stock Analyzer Pro
Works with the AI Agents you already use
Quantitative Stock Analyzer Pro
Professional quantitative workflow for walk-forward backtesting, tail-risk CVaR analysis, and portfolio optimization.
$5
Quantitative Stock Analyzer Pro
Example session with this skill installed
Analyze a long-only strategy for AAPL, MSFT, and GOOGL. Use a 12-month training window and 3-month test window. Calculate 95% CVaR and optimize weights to minimize risk with a 40% max weight cap.
- Read your context and instructions
- Compiled the quantitative stock analyzer
I have completed the quantitative analysis for the requested asset universe. The audit confirmed 5 years of daily adjusted closing prices with no missing values. The walk-forward simulation covered 16 rolling folds.
Strategy Research & Risk Audit
| Metric | Aggregate Out-of-Sample | Benchmark (SPY) |
|---|---|---|
| Annualized Return | 14.2% | 10.8% |
| Annualized Volatility | 18.5% | 15.2% |
| Max Drawdown | -22.1% | -19.4% |
| Sharpe Ratio (Rf=2%) | 0.66 | 0.58 |
| 95% CVaR (Monthly) | -8.4% | -7.1% |
Optimized Portfolio Weights
- AAPL: 35.0%
- MSFT: 40.0% (At Cap)
- GOOGL: 25.0%
- Status: Feasible. Minimized CVaR objective met within all constraints.
HTML Research Report
<!DOCTYPE html>
<html>
<head>
<title>Quant Research Report - AAPL/MSFT/GOOGL</title>
<style>body{font-family:sans-serif;margin:40px;line-height:1.6;} .metric-box{border:1px solid #ddd;padding:15px;}</style>
</head>
<body>
<h1>Quantitative Strategy Analysis</h1>
<section>
<h2>Walk-Forward Results</h2>
<p>The rolling window analysis indicates stable out-of-sample performance, though turnover increased during Fold 12 (Q3 2022).</p>
</section>
<section>
<h2>Tail Risk (CVaR)</h2>
<p>Historical 95% CVaR is -8.4%, indicating the average loss in the worst 5% of monthly outcomes.</p>
</section>
</body>
</html>
Next steps
- Review the Fold 12 performance to understand the turnover spike during that market regime.
- Adjust the CVaR confidence level to 99% for a more conservative stress test.
- Test sensitivity to transaction costs by increasing slippage assumptions from 5bps to 15bps.
Connects securely to your tools. The creator never sees your data.
About this skill
Quantitative strategies often fail in production because of look-ahead bias and overfitting. This skill enforces a rigorous walk-forward backtesting and risk management workflow to validate asset strategies before deployment.
What it does
- Walk-forward testing splits historical data into sequential training and out-of-sample windows to prevent data leakage.
- Tail-risk assessment calculates Conditional Value at Risk (CVaR) and Expected Shortfall to model extreme loss scenarios beyond standard volatility.
- Constrained optimization generates portfolio weights based on specific objectives like minimizing CVaR or maximizing returns within sector and turnover limits.
- Data auditing identifies missing values, ticker outliers, and alignment issues across multiple asset histories.
- HTML reporting produces self-contained research files with embedded charts and metrics for local review without external dependencies.
How it works
- Input Audit: Provide tickers, historical price data, and strategy parameters for a data quality check.
- Strategy Specification: Define entry/exit rules, transaction costs, and portfolio constraints.
- Execution: The agent runs the walk-forward simulation and CVaR calculations across defined time folds.
- Report Generation: Receive a full performance breakdown and an HTML research document.
Frameworks & tools
This skill is designed for quantitative research environments using historical price/return data. It focuses on mathematical validation of strategies through statistical risk metrics and constrained optimization logic.
Why this beats prompting it yourself
Standard prompts often produce "backtests" that suffer from survivorship bias and look-ahead errors. This skill forces a rolling window methodology that treats every test period as unseen data, ensuring your results are mathematically defensible and reproducible.
Use cases
- Validate a moving average crossover strategy using out-of-sample rolling windows.
- Optimize a multi-asset portfolio to minimize tail risk during market stress.
- Audit a proposed trading strategy for data leakage and transaction cost sensitivity.
- Generate a professional quantitative research report for a new investment thesis.
Known limitations
Requires external historical data as it does not fetch live market prices. Optimization results are model-dependent and assume constraint feasibility.
Requires historical price/return data inputs. Does not fetch live market data. Optimization results assume mathematical feasibility within provided constraints.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 18 days ago
Permissions
No special permissions declared or detected