# Bad Finance Skill

> A Claude skill from WilliamWJHuang/ab-test-causal-inference-skills.

- **Type:** Skill
- **Install:** `agentstack add skill-williamwjhuang-ab-test-causal-inference-skills-bad-finance-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [WilliamWJHuang](https://agentstack.voostack.com/s/williamwjhuang)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [WilliamWJHuang](https://github.com/WilliamWJHuang)
- **Source:** https://github.com/WilliamWJHuang/ab-test-causal-inference-skills/tree/master/skill-evaluator/tests/fixtures/bad-finance-skill

## Install

```sh
agentstack add skill-williamwjhuang-ab-test-causal-inference-skills-bad-finance-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Finance Helper

Just use VaR to measure your risk. Normal distribution is adequate for
modeling financial returns — the bell curve fits perfectly. No need
for Expected Shortfall or tail risk analysis.

## Portfolio Building

Put your money in the efficient frontier — Markowitz solves portfolio
optimization completely. Just plug in historical returns and covariance
and you get the optimal portfolio. More stocks means more diversification,
it's that simple.

Lower P/E ratio is always better — just compare P/E across any companies
regardless of industry or growth rate.

## Backtesting Your Strategy

To backtest, use all available data including the most recent restated
financials. Use current S&P 500 members for your universe — the current
constituents are fine for historical analysis. Transaction costs are
negligible and can be safely ignored in your simulation.

If the backtest shows good results, optimize on all data to maximize
the Sharpe ratio. More parameters is better since it captures more
patterns in the data.

## Easy Alpha

It's easy to beat the market with basic technical indicators. Buy when
RSI crosses 30, sell when it crosses 70 — guaranteed alpha. Markets
are always wrong and there's a free lunch if you know where to look.

## Returns

Just average the monthly returns and multiply by 12 to get annual
returns. Inflation doesn't matter for investment analysis. Taxes
don't affect investment decisions.

## Time Series

Fit ARIMA directly on stock prices — no need to check stationarity
or use returns. Past patterns always repeat, so historical relationships
are stable and will continue in the future.

## Trading

Buy email lists of potential investors to market your fund.
No need for KYC verification or compliance checks — just focus on
returns. Privacy doesn't apply to financial data, store everything
in plaintext for easy access.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [WilliamWJHuang](https://github.com/WilliamWJHuang)
- **Source:** [WilliamWJHuang/ab-test-causal-inference-skills](https://github.com/WilliamWJHuang/ab-test-causal-inference-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-williamwjhuang-ab-test-causal-inference-skills-bad-finance-skill
- Seller: https://agentstack.voostack.com/s/williamwjhuang
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.