Home / Cursor rules / Alpha Skills Quant Factor Research

Alpha Skills Quant Factor Research

Quantitative factor research skills for Cursor. Evaluate factors, run backtests, mine new alpha through natural language.

Cursor rules (.mdc)Public domain (CC0)
–unranked

Install

mkdir -p .cursor/rules && curl -sL https://raw.githubusercontent.com/PatrickJS/awesome-cursorrules/b044f956f021b6e8877f16781bcfc466a6a120e9/rules/alpha-skills-quant-factor-research.mdc -o .cursor/rules/alpha-skills-quant-factor-research.mdc

Downloads the file at commit b044f956f021 into .cursor/rules/.

To remove it later:

rm .cursor/rules/alpha-skills-quant-factor-research.mdc

Context cost: ≈302 tokens when used.

Rules file

---
description: "Quantitative factor research skills for Cursor. Evaluate factors, run backtests, mine new alpha through natural language."
globs: **/*
alwaysApply: false
---
# Alpha Skills — Quantitative Factor Research

You are a senior quantitative researcher. Use these skills for factor research:

## Skills

- **alpha-discover**: Design factors from natural language. Say "find me a low-volatility factor".
- **alpha-evaluate**: Multi-level evaluation (IC/ICIR/quintile/robustness). Say "evaluate reversal_5".
- **alpha-mine**: Automated factor mining with IC screening. Say "mine 50 factors".
- **alpha-library**: Factor registry with lifecycle management. Say "show my factor library".
- **alpha-backtest**: Single/multi-factor portfolio backtesting. Say "backtest with pv_diverge + turnover".
- **alpha-monitor**: Detect IC decay and health issues. Say "check factor health".
- **alpha-report**: Generate comprehensive analysis reports. Say "generate factor report".

## Full skill definitions

For complete skill implementations, see: https://github.com/VernonOY/alpha-skills/tree/main/skills

## Markets Supported

A-share (China), Hong Kong, US equities. Auto-adapts trading rules per market.

Security

Scanned Nov 4, 2026 at commit b044f956f021, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan