multi-factor

Official

Rank stocks with multi-factor confidence.

AuthorHKUDS
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill solves the challenge of manually identifying high-conviction long candidates across many stocks by computing and blending multiple cross-sectional factors then maintaining stable portfolio weights across rebalance windows.

Core Features & Use Cases

  • Composite Scoring: Calculates momentum, reversal, volatility, and volume ratio, standardizes them via Z-score, and sums them into a unified ranking.
  • TopN Portfolio Signals: Selects the highest-scoring securities, assigns equal long weights, and reuses the previous signal between rebalance dates to avoid churn during a real-world trading cycle.
  • Use Case: Deploy this engine to score China A-share or global holdings, optionally add 1/PE, 1/PB, or ROE when available, and rebalance every 20 trading days to keep exposures fresh yet stable.

Quick Start

Ask the skill to score your cross-sectional stock universe, normalize the factors, and return the TopN equal-weight names.

Dependency Matrix

Required Modules

pandasnumpyrequests

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: multi-factor
Download link: https://github.com/HKUDS/Vibe-Trading/archive/main.zip#multi-factor

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.