Skip to content
Get packs

Risk Measurement and Stress Testing

Computes VaR, CVaR, drawdowns and Monte Carlo risk simulations with consistent sign conventions

Source Download skill
Repository
HKUDS/Vibe-Trading
Stars
37,433
Licence
MIT
Files
1 file

What it does

When this skill is installed, the agent uses a shared set of risk formulas (Value at Risk, Conditional VaR, maximum drawdown, Monte Carlo price simulation and tail-risk fitting) instead of rewriting them from memory. It reports losses as positive numbers, warns about common mistakes such as assuming the parametric method always understates risk, and asks for reproducible random seeds. It is aimed at evaluating backtests and portfolio risk limits.

Great for

  • Quantitative analysts checking the downside risk of a trading strategy or backtest
  • Developers building risk dashboards or portfolio risk controls in Python
  • Students learning how VaR, CVaR and drawdown are defined and compared

Skip it if

  • Personal investment or trading decisions: the skill gives statistical estimates from historical or simulated data, which can badly understate real losses in unusual markets
  • Regulatory or compliance reporting that requires audited models, since the skill is a methodology guide and not a certified implementation

Try asking

  • “Calculate the 99% 10-day historical VaR and CVaR for this daily return series”
  • “Compute the maximum drawdown and recovery date for this equity curve”
  • “Run a 10,000-path Monte Carlo simulation of a stock with 10% annual drift and 20% volatility, using a fixed seed”
  • “Compare parametric and historical VaR at 99% and explain the difference”
Step-by-step guide: how to use Risk Measurement and Stress TestingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    risk-analysis.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip risk-analysis.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip risk-analysis.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Always state the confidence level and horizon when quoting VaR or CVaR so results can be compared
  • Pass an explicit seed to Monte Carlo runs so the numbers in a report can be reproduced
  • Treat outputs as estimates from past or simulated data and check them against stress scenarios before relying on them

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/Vibe-Trading under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.