Analyze yfinance portfolio returns to generate risk metrics and allocation recommendations.
npx skills add https://github.com/phanijapps/zbot --skill yf-risk
Please help me install this Agent Skill. Skill: yf-risk Source: https://github.com/phanijapps/zbot/tree/main/gateway/templates/skills/yf-risk Command: npx skills add https://github.com/phanijapps/zbot --skill yf-risk
Perform portfolio construction and risk diagnostics directly from yfinance multi-asset return series. Use when an agent needs correlation analysis, drawdown and VaR metrics, stress scenarios, or weight optimization for stock, ETF, and crypto portfolios.
Compute risk metrics and a risk-aware allocation from the aligned yfinance return streams.
High-intent search queries and answers about installing and using this skill.
Compute portfolio risk metrics from yfinance data by generating an aligned return matrix to deliver annualized return, volatility, Sharpe ratio, max drawdown, VaR, and CVaR diagnostics for stock, ETF, and crypto portfolios.
You can optimize portfolio weights with explicit constraints using yfinance return series to generate an optional optimized allocation that aligns with your risk diagnostics and scenario limits.
The best way to run stress tests on a mixed-asset portfolio is by applying market shock and volatility spike scenarios to yfinance return streams, producing stress-test summaries for stocks, ETFs, and crypto assets.
Yes, portfolio risk analytics supports correlation analysis for crypto and ETFs by computing an aligned return matrix from yfinance data, enabling rolling correlation checks across mixed-asset portfolios.
Generate a risk metrics table for stock and ETF portfolios by processing aligned yfinance return streams to calculate annualized volatility, Sharpe ratio, drawdown, and VaR/CVaR values.
Use yfinance return series for portfolio construction when you need direct risk diagnostics, correlation analysis, and weight optimization for stock, ETF, and crypto portfolios without external data dependencies.
koukoCompute technical indicators from OHLCV data into structured snapshot cards.
mahmoud20138Construct optimized multi-asset portfolios using mean-variance, risk parity, HRP, and Black-Litterman models.
ccfCompute VaR, CVaR, drawdown, and risk-adjusted returns from pandas return series.
ebrahim-saniCompute portfolio VaR, CVaR, and maximum drawdown across historical, parametric, and Monte Carlo methods.
