# Build and Evaluate Quantitative Strategies

Quantitative research requires consistent data, statistical methods, and validation. This skill structures Longbridge workflows for analysis, screening, optimization, execution, and hedging.

## Install

```bash
npx skillstore add longbridge/longbridge-quant
```

## Metadata

- Status: approved
- Slug: longbridge-longbridge-quant
- Version: 1.0.0
- Author version: 1.0.0
- Skillstore revision: r2
- Version status: not\_bumped
- Tree hash: cb725f9923abf588abf0bc09a6c79d1d8c7a939eb7df3231bc5e79ff373d6e20
- Author: longbridge
- GitHub username: longbridge
- License: MIT
- Repository: https://github.com/longbridge/skills/tree/main/skills/longbridge-quant
- Ref: 656be3040aef5c047555a908cd5c695d22a4a548
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 69
- Public page: https://skillstore.pages.dev/skills/longbridge-longbridge-quant
- Manifest: https://skillstore.pages.dev/api/skills/longbridge-longbridge-quant/manifest

## Capabilities

- Builds pairs-trading workflows using cointegration, hedge ratios, Z-scores, and mean-reversion signals.
- Screens and ranks stocks with valuation, quality, growth, momentum, and volatility factors.
- Analyzes seasonality, correlation, ADF tests, GARCH volatility, regression diagnostics, and bootstrap results.
- Structures grid search, walk-forward validation, and out-of-sample checks for strategy optimization.
- Designs execution-cost models and portfolio hedges using market, options, and position data.
- Runs Navi or Pine-compatible indicator scripts against Longbridge K-line data through the quant CLI.

## Use Cases

- Research a Trading Pair: Test cointegration, estimate a hedge ratio, and define entry and exit signals from historical prices.
- Rank an Equity Universe: Screen index constituents and compare factor scores using valuation, momentum, quality, and volatility measures.
- Validate a Strategy: Create parameter searches and walk-forward tests that separate in-sample and out-of-sample performance.

## Prompt Templates

### Explain a Quantitative Method

```
Explain [METHOD] for [SYMBOL OR UNIVERSE]. Define required data, calculations, assumptions, outputs, and major risks.
```

### Screen a Stock List

```
Screen [SYMBOLS OR INDEX] using [FACTORS] and [THRESHOLDS]. Rank passing symbols, explain weights, identify missing data, and cite the data source.
```

### Design a Backtest

```
Design a backtest for [STRATEGY] on [SYMBOLS] over [PERIOD]. Include signals, costs, position sizing, metrics, and out-of-sample validation.
```

### Optimize and Stress Test a Portfolio Strategy

```
Optimize [STRATEGY] across [PARAMETER RANGES]. Use walk-forward validation, quantify degradation, model execution costs, test hedge scenarios, and flag overfitting.
```

## Limitations

- Most workflows depend on Longbridge CLI or MCP access and available market data.
- Indicator scripts are submitted to Longbridge for server-side execution.
- Portfolio-position analysis requires login and trade-scope access.
- Historical patterns, backtests, and model signals do not predict future returns.

## Best Practices

- Confirm symbols, markets, date ranges, and data frequency before analysis.
- Include transaction costs, slippage, liquidity, and out-of-sample validation in every backtest.
- Request consent before remote script submission or authenticated portfolio access.

## Anti Patterns

- Do not present historical performance or model signals as guaranteed future returns.
- Do not optimize parameters only on the full dataset without an untouched validation period.
- Do not install packages, submit proprietary scripts, or read portfolio positions without approval.

## Security Audit

- Audited at: 2026-08-08T09:51:03.388\+00:00
- Summary: Most static findings mistake Markdown backticks or ordinary financial terminology for shell execution or reconnaissance. Remote indicator execution can disclose submitted scripts, and the hedging workflow accesses authenticated portfolio positions despite public-access metadata.

## Stats

- Views: 0
- Downloads: 9
- Favorites: 2
- Popularity score: 0