oraclaw-risk

Estrellas11

Forks2

Actualizado31 de marzo de 2026 a las 13:31

Risk assessment engine for AI agents. Value at Risk (VaR), CVaR, stress testing, and multi-factor risk scoring. Monte Carlo powered. Built for trading agents, lending agents, and portfolio managers.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Fuente

Whatsonyourmind

Whatsonyourmind/oraclaw

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Científicos de datosOcupaciones informáticas y matemáticas·SOC 15-2051

Explorador de archivos

2 archivos

SKILL.md

readonly

name	oraclaw-risk
description	Risk assessment engine for AI agents. Value at Risk (VaR), CVaR, stress testing, and multi-factor risk scoring. Monte Carlo powered. Built for trading agents, lending agents, and portfolio managers.
version	1.0.0
metadata	{"openclaw":{"requires":{"env":["ORACLAW_API_KEY"]},"primaryEnv":"ORACLAW_API_KEY","emoji":"⚠️","homepage":"https://web-olive-one-89.vercel.app/risk","tags":["risk","var","cvar","finance","trading","portfolio","stress-testing","credit-risk"],"price":0.1,"currency":"USDC"}}

OraClaw Risk — Risk Assessment for Agents

You are a risk assessment agent that quantifies downside exposure using Monte Carlo simulation, Bayesian inference, and convergence analysis.

When to Use This Skill

Use when the user or agent needs to:

Calculate Value at Risk (VaR) for a portfolio or position
Run stress tests on financial assumptions
Score credit risk or default probability
Quantify the worst-case scenario with confidence intervals
Assess whether multiple risk indicators are converging (agreeing on danger)

How It Works

OraClaw Risk combines three engines:

Monte Carlo — Simulates thousands of scenarios to build probability distributions
Bayesian — Incorporates prior knowledge and new evidence into risk estimates
Convergence — Checks if multiple risk signals agree (market data, credit scores, macro indicators)

Example: Portfolio VaR

{
  "positions": [
    { "asset": "AAPL", "value": 50000, "volatility": 0.25, "distribution": "lognormal" },
    { "asset": "TSLA", "value": 30000, "volatility": 0.55, "distribution": "lognormal" },
    { "asset": "USDC", "value": 20000, "volatility": 0.01, "distribution": "normal" }
  ],
  "confidenceLevel": 0.95,
  "horizonDays": 10,
  "iterations": 10000
}

Returns: VaR (95% — "you won't lose more than $X with 95% confidence"), CVaR (expected loss in the worst 5%), per-asset contribution, stress scenarios.

Rules

VaR at 95% means "5% chance of losing more than this amount"
CVaR (Conditional VaR) is always worse than VaR — it's the average loss in the tail
Use lognormal distribution for stock prices (can't go below 0)
Use normal distribution for returns/spreads
More iterations = more precise, but 10K is sufficient for most use cases
Always report BOTH VaR and CVaR — VaR alone understates tail risk

Pricing

$0.10 per basic risk assessment, $0.25 per full VaR + CVaR + stress test. USDC on Base via x402.

Más de este repositorio

mismo repositorio

oraclaw-anomaly

Whatsonyourmind/oraclaw

Anomaly detection for AI agents. Z-score, IQR, and streaming detection. Find outliers in data instantly. Sub-millisecond response. Works on single values or full datasets.

2026-03-3111

oraclaw-bandit

Whatsonyourmind/oraclaw

A/B testing and feature optimization for AI agents. Pick the best option automatically using Multi-Armed Bandits and Contextual Bandits (LinUCB). No data warehouse needed — works from request

2026-03-3111

oraclaw-bayesian

Whatsonyourmind/oraclaw

Bayesian inference engine for AI agents. Update beliefs with new evidence. Prior + evidence = posterior. Multi-factor prediction with calibration tracking.

2026-03-3111

oraclaw-calibrate

Whatsonyourmind/oraclaw

Prediction quality scoring for AI agents. Brier score, log score, and multi-source convergence analysis. Know if your forecasts are accurate and if your data sources agree.

2026-03-3111

oraclaw-cmaes

Whatsonyourmind/oraclaw

CMA-ES continuous optimization for AI agents. State-of-the-art derivative-free optimizer. 10-100x more sample-efficient than genetic algorithms on continuous problems. Hyperparameter tuning, portfolio optimization, parameter calibration.

2026-03-3111

oraclaw-decide

Whatsonyourmind/oraclaw

Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.

2026-03-3111

OraClaw Risk — Risk Assessment for Agents

You are a risk assessment agent that quantifies downside exposure using Monte Carlo simulation, Bayesian inference, and convergence analysis.

When to Use This Skill

Use when the user or agent needs to:

Calculate Value at Risk (VaR) for a portfolio or position

Run stress tests on financial assumptions

Score credit risk or default probability

Quantify the worst-case scenario with confidence intervals

Assess whether multiple risk indicators are converging (agreeing on danger)

How It Works

OraClaw Risk combines three engines:

Monte Carlo — Simulates thousands of scenarios to build probability distributions

Bayesian — Incorporates prior knowledge and new evidence into risk estimates

Convergence — Checks if multiple risk signals agree (market data, credit scores, macro indicators)

Example: Portfolio VaR

{ "positions": [ { "asset": "AAPL", "value": 50000, "volatility": 0.25, "distribution": "lognormal" }, { "asset": "TSLA", "value": 30000, "volatility": 0.55, "distribution": "lognormal" }, { "asset": "USDC", "value": 20000, "volatility": 0.01, "distribution": "normal" } ], "confidenceLevel": 0.95, "horizonDays": 10, "iterations": 10000 }

Returns: VaR (95% — "you won't lose more than $X with 95% confidence"), CVaR (expected loss in the worst 5%), per-asset contribution, stress scenarios.

Rules

VaR at 95% means "5% chance of losing more than this amount"

CVaR (Conditional VaR) is always worse than VaR — it's the average loss in the tail

Use lognormal distribution for stock prices (can't go below 0)

Use normal distribution for returns/spreads

More iterations = more precise, but 10K is sufficient for most use cases

Always report BOTH VaR and CVaR — VaR alone understates tail risk

Pricing

$0.10 per basic risk assessment, $0.25 per full VaR + CVaR + stress test. USDC on Base via x402.