Longbridge Quant

Quantitative frameworks with data attached: pairs trading, volatility regimes, seasonality, multi-factor models, factor research, and walk-forward optimization.

⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. Backtested performance is hypothetical, is easy to overfit, and does not survive contact with live markets unchanged. Curated by Skill Harbor: the quantitative skill of the Longbridge platform, published by the broker itself. It pairs a set of strategy frameworks with a quant CLI command that runs indicator scripts against K-line data pulled through Longbridge. The frameworks cover pairs trading and statistical arbitrage (Engle-Granger cointegration, OLS hedge ratio, z-score signals, half-life of mean reversion); volatility regime strategies that switch between long-volatility and short-volatility structures on historical volatility percentiles; seasonality and calendar effects (month of year, day of week, holiday drift, earnings season); a multi-factor model combining value, momentum, quality and low volatility into a z-score composite with a top-N portfolio; factor research with IC and IR analysis, factor decay and layered backtests; factor screening on valuation, profitability, growth and yield filters; correlation and Johansen cointegration analysis; a statistics toolkit (ADF unit-root tests, GARCH modeling, bootstrap); a strategy optimizer built on parameter sweeps and walk-forward validation; an execution model for slippage, VWAP and TWAP logic and market impact; hedging design (beta hedging, options protection, tail risk, cross-asset); and a machine learning layer using walk-forward Random Forest and Gradient Boosting from scikit-learn. The quant command is public and the frameworks are analytical, no login required. From the longbridge/skills repository (MIT). Honest caveats: cointegration breaks, factors decay, and seasonality is the easiest effect to data-mine by accident; the skill supplies method and computation, and the discipline of out-of-sample checking it includes is the part to actually follow. Skill Harbor never reviews the code, review it yourself before use.

At a glance

What: Quantitative frameworks with data attached: pairs trading, volatility regimes, seasonality, multi-factor models, factor research, and walk-forward optimization.
Cost: Free
Needs: Use "Longbridge Quant" with your Muse.
Install: Copy the installer prompt below into your Muse — your agent does the rest.

⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. Backtested performance is hypothetical, is easy to overfit, and does not survive contact with live markets unchanged. Curated by Skill Harbor: the quantitative skill of the Longbridge platform, published by the broker itself. It pairs a set of strategy frameworks with a quant CLI command that runs indicator scripts against K-line data pulled through Longbridge. The frameworks cover pairs trading and statistical arbitrage (Engle-Granger cointegration, OLS hedge ratio, z-score signals, half-life of mean reversion); volatility regime strategies that switch between long-volatility and short-volatility structures on historical volatility percentiles; seasonality and calendar effects (month of year, day of week, holiday drift, earnings season); a multi-factor model combining value, momentum, quality and low volatility into a z-score composite with a top-N portfolio; factor research with IC and IR analysis, factor decay and layered backtests; factor screening on valuation, profitability, growth and yield filters; correlation and Johansen cointegration analysis; a statistics toolkit (ADF unit-root tests, GARCH modeling, bootstrap); a strategy optimizer built on parameter sweeps and walk-forward validation; an execution model for slippage, VWAP and TWAP logic and market impact; hedging design (beta hedging, options protection, tail risk, cross-asset); and a machine learning layer using walk-forward Random Forest and Gradient Boosting from scikit-learn. The quant command is public and the frameworks are analytical, no login required. From the longbridge/skills repository (MIT). Honest caveats: cointegration breaks, factors decay, and seasonality is the easiest effect to data-mine by accident; the skill supplies method and computation, and the discipline of out-of-sample checking it includes is the part to actually follow. Skill Harbor never reviews the code, review it yourself before use.

Version:

@

Created by: @longbridge

Not verified? How to check before you trust →

Install — Free · open source (MIT) View source code

⌁

Install

Copy the install package below, then paste it into Muse

Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a build before installing →

After installation, ask me if I want to leave private feedback
Private for now: only the Skill Harbor team sees it. Sellers may be looped in later.

Use "Longbridge Quant" with your Muse. Prerequisites: install the Longbridge CLI once (brew tap longbridge/tap && brew install longbridge/tap/longbridge-terminal) or connect the Longbridge MCP server, and clone the repo (git clone https://github.com/longbridge/skills) so the skill's reference files are on hand. No Longbridge account is required. The machine learning framework needs Python with scikit-learn (pip install scikit-learn); statistical tests need enough history, at least about 50 observations for an ADF test. 1. Open the skill: https://github.com/longbridge/skills/blob/main/skills/longbridge-quant/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Test these two tickers for cointegration on two years of daily data, and report the hedge ratio, z-score, and half-life before suggesting any trade structure." 3. For any strategy result, ask which part of the sample was held out of sample; if everything was in sample, treat the numbers as a hypothesis, not evidence. Tip: run the factor research (IC/IR and decay) before the multi-factor portfolio; a factor that no longer predicts anything only adds turnover. Safety: a skill is plain-text instructions; it runs nothing by itself. Informational only, not investment advice.

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.