longbridge-quant

description: Curated upstream guidance for Longbridge Quant; use when the workflow matches the user goal.name: longbridge-quantlicense: MITmetadata:   author: longbridge  version: 1.0.0  risk_level: read_only  requires_login: false  default_install: true  requires_mcp: false  tier: readsource_repo: longbridge/skillssource_type: officialsource: longbridgedate_added: '2026-09-21'risk: critical

When to Use

• Use when this upstream workflow matches the user's stated goal.
• Use when the task requires the procedures documented in this skill.

Longbridge Quant

Quantitative analysis frameworks and CLI indicator scripting via Longbridge.

Response language: match the user's input language — English / Simplified Chinese / Traditional Chinese. RULE: Response language priority: English is the default when language is ambiguous. If the user input is only a slash command, command name, ticker / symbol, or contains no natural-language language signal, you MUST respond in English. Do not infer Chinese from trigger keywords, skill metadata, or examples.

Data-source scope: this skill documents Longbridge. If its data is unavailable or insufficient, report the gap rather than inventing data or asserting that other sources are disallowed.

Connector availability: discover the tools actually available in the host; do not assume a Longbridge plugin or parity with CLI capabilities.

When to Use

Trigger when user asks about: quantitative indicator scripts (running against K-line data), pairs trading / cointegration, volatility regime strategies, seasonality / calendar effects, multi-factor stock selection, factor research (IC/IR analysis), factor screening, correlation and cointegration analysis, statistical methods (ADF/GARCH/bootstrap), strategy optimization, execution cost modeling, hedging strategies, or ML-based prediction.

Sub-topic Routing

CLI: quant

The quant command runs user-defined indicator scripts against K-line data.

longbridge quant --help

Use longbridge kline <SYMBOL> --format json (from longbridge-market-data) to obtain OHLCV input data.

Quantitative Frameworks

Pairs Trading / Statistical Arbitrage

Engle-Granger cointegration, hedge ratio via OLS, Z-score, half-life of mean reversion, entry/exit signals. See [references/pairs-trading.md].

Volatility Strategy

20-day / 60-day HV, percentile rank, long-vol (buy straddle) vs short-vol (iron condor) regime signals. See [references/volatility-strategy.md].

Seasonality / Calendar Effects

Month-of-year returns (January Effect), day-of-week effects, pre/post-holiday drift, earnings season effect. See [references/seasonality.md].

Multi-Factor Model

Value (1/PE, 1/PB), momentum (60-day), quality (ROE), low-vol (60-day HV) — Z-score composite, TopN portfolio. See [references/multifactor.md].

Factor Research

IC, IR, factor decay, layer backtest, IC-weighted combination. See [references/factor-research.md].

Factor Screening

Batch screening with PE, PB, ROE, revenue growth, dividend yield filters. See [references/factor-screen.md].

Correlation & Cointegration

Pairwise return correlation, rolling correlation, Johansen test. See [references/correlation.md].

Quantitative Statistics

ADF unit-root test, GARCH volatility modeling, regression diagnostics, bootstrap. See [references/quant-stats.md].

Strategy Optimizer

Parameter sweep, walk-forward optimization, out-of-sample validation. See [references/strategy-optimizer.md].

Execution Model (Backtest)

Slippage formulas (linear / square-root), VWAP/TWAP logic, market impact estimation. See [references/execution-model.md].

Hedging Strategy

Beta hedging, options protection, tail-risk hedging, cross-asset hedging. See [references/hedging.md].

ML Strategy (sklearn)

Rolling walk-forward Random Forest / Gradient Boosting, feature engineering, signal generation. See [references/ml-strategy.md].

Auth requirements

quant execution is analytical but sends the supplied script to a remote service. Market-data access can require login/entitlements; positions require explicit account-access scope. Verify installed CLI capabilities and current permissions. Do not submit proprietary strategy code without authorization.

Error handling

MCP fallback

Use MCP server for kline data if CLI unavailable. Discover tools at runtime.

Related skills

File layout

longbridge-quant/
├── SKILL.md
└── references/
    ├── quant-cli.md
    ├── pairs-trading.md · volatility-strategy.md · seasonality.md
    ├── multifactor.md · factor-research.md · factor-screen.md · correlation.md
    ├── quant-stats.md · strategy-optimizer.md · execution-model.md
    └── hedging.md · ml-strategy.md

Examples

User: Apply this skill to my current task.
Assistant: Follow the workflow in this skill, cite limitations, and ask before risky steps.

Limitations

• This skill performs analysis, not order execution. Strategy descriptions are hypotheses requiring realistic costs, liquidity, borrow/margin and out-of-sample validation. Do not invent recommendations from missing data.

• For historical research, require point-in-time constituents and fundamentals with publication timestamps; current values cannot support a historical factor backtest. Adjust prices for corporate actions and align currency, timestamps and trading calendars.

• Cite Longbridge only when data was actually retrieved there; report its timestamp, coverage and adjustments. Redact credentials/private account data from errors and reports.

• Imported upstream skill; verify credentials, permissions, and safety boundaries before execution.

• Does not replace environment-specific validation, testing, or maintainer review.