oraclaw-risk

Estrelas11

Forks2

Atualizado31 de março de 2026 às 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.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

Whatsonyourmind

Whatsonyourmind/oraclaw

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Cientistas de dadosInformática e Matemática·SOC 15-2051

Explorador de arquivos

2 arquivos

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.

Mais deste repositório

mesmo repositório

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

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.