Bad finance skill

Skill WilliamWJHuang/ab-test-causal-inference-skills/skill-evaluator/tests/fixtures/bad-finance-skill

Agent skills for experiment design, causal inference, and statistical review. One install, adapts to your level.From the repository description

Install

npx -y skills add WilliamWJHuang/ab-test-causal-inference-skills --skill bad-finance-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 388 tokens by cl100k_base, as published. Nobody here has run it

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.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most finance skills give in 388 tokens

Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07

Extract date vendor amount and descriptionin 15 of 469, across 3 files
Scan folder for invoice filesin 14 of 469, across 2 files
Rename files to standard formatin 14 of 469, across 2 files
Show organization plan before movingin 14 of 469, across 2 files
Generate summary CSVin 14 of 469, across 2 files
Organize files by categoryin 13 of 469, across 1 file
Preserve original filesin 13 of 469, across 1 file
Flag files missing critical infoin 13 of 469, across 1 file
Produce the requested output filein 9 of 469, across 4 files
Build best, base, and worst case scenariosin 9 of 469, across 5 files
Implement backoff if rate limit errors occurin 8 of 469, across 3 files
Determine the weighted average cost of capitalin 8 of 469, across 4 files

Said here and by no other author read

model returns using a normal distribution
build portfolios using Markowitz optimization
add more stocks to increase diversification
prefer stocks with lower P/E ratios
use current index constituents for historical analysis
ignore transaction costs in backtests

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.