Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/hft-quant-expert
Quantitative trading expertise for DeFi and crypto derivatives.
Passed 21 of 22 test cases with the skill, and 16 of 22 without it.
and 3 more in the full report
5 fixed16 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am modeling statistical arbitrage on Solana pools. I have estimated the mean reversion rate coefficient (lambda) from autoregressive modeling. Provide the mathematical formula or Python line to compute the spread half-life.
| Checked | Without skill | With skill |
|---|---|---|
| Uses -np.log(2) / lambda to calculate the half-life of mean reversion | Missed | Passed |
The instructions your model reads when the skill loads.
Quantitative trading expertise for DeFi and crypto derivatives.
Calculate z-score or other entry signal.
Use Kelly Criterion (0.25x) for position sizing.
Check for lookahead bias, survivorship bias, overfitting.
Include gas + slippage in profit calculations.
# Z-score
zscore = (value - rolling_mean) / rolling_std
# Sharpe (annualized)
sharpe = np.sqrt(252) * returns.mean() / returns.std()
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.