/vkkm:backtest

Validate VaR models with the Kupiec POF test and Basel traffic light system.

2|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/Vaibhavkkm/vkkm-aegis-plugin --skill vkkm-backtest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /vkkm:backtest
Source: https://github.com/Vaibhavkkm/vkkm-aegis-plugin/tree/main/skills/backtest
Command: npx skills add https://github.com/Vaibhavkkm/vkkm-aegis-plugin --skill vkkm-backtest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the validation of Value at Risk (VaR) models, ensuring they meet regulatory standards and accurately reflect potential financial losses.

Core Features & Use Cases

  • Kupiec Test Execution: Performs the Basel-mandated Proportion of Failures (POF) test to assess VaR model accuracy.
  • Traffic Light Classification: Classifies model performance into Green, Yellow, or Red zones based on exception rates.
  • Exception Clustering Analysis: Identifies patterns of consecutive VaR breaches, indicating potential volatility clustering issues.
  • Use Case: A risk manager needs to submit their firm's VaR model for regulatory review. This Skill can quickly assess the model's historical performance against actual P&L data, providing a clear pass/fail verdict and actionable insights.

Quick Start

Validate my 99% 1-day VaR model which estimated €50,000 daily VaR, given 250 trading days with 8 exceptions.

Frequently Asked Questions about /vkkm:backtest

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

FAQPage Schema
How do I validate my VaR model using the Kupiec test?

To validate a VaR model using the Kupiec test, you compare your Value at Risk estimates against actual P&L time series data. This Skill performs the Proportion of Failures test to assess model accuracy and classifies results into Basel traffic light zones based on exception rates.

What is the Basel traffic light system for VaR exception clustering?

The Basel traffic light system categorizes VaR model performance into Green, Yellow, or Red zones based on the number of exceptions. This Skill analyzes your P&L time series to identify exception clustering and consecutive VaR breaches, indicating potential volatility clustering issues.

Can I run a backtest for a 99% 1-day VaR model with 250 trading days?

Yes, you can backtest a 99% 1-day VaR model using 250 trading days of data. The Skill accepts your VaR estimates and actual P&L data to calculate the exception rate, providing a clear pass or fail verdict with regulatory context for compliance.

Does this backtesting Skill support offline parametric calculations?

Yes, this Skill supports both online Python MCP calculations and offline parametric calculations for VaR backtesting. It provides data-grounded or illustrative estimates depending on your available inputs and environment setup.

Why does my VaR model show consecutive breaches and fail the POF test?

Consecutive VaR breaches indicate exception clustering, often caused by volatility clustering issues in your P&L time series. Failing the Proportion of Failures test means your model inaccurately reflects potential financial losses and requires recalibration to meet regulatory standards.