A guided assistant for creating quantitative stock selection strategies and generating executable YAML configuration files for the quantcli toolchain.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install multi-factor-strategy
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install multi-factor-strategy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Multi-Factor Strategy Assistant?
The Multi-Factor Strategy Assistant is a specialized tool designed to bridge the gap between financial theory and quantitative execution using Openclaw Skills. It helps developers and traders define complex screening criteria, select technical and fundamental factors, and assign weights to create a unified ranking system. By automating the creation of YAML configuration files, it ensures that your stock selection logic is portable, reproducible, and ready for use with the quantcli framework.
Whether you are building a value-based long-term portfolio or a high-frequency momentum strategy, this skill provides the mathematical rigor and structural clarity required for modern quantitative analysis. It streamlines the workflow from conceptualizing a strategy to generating the final code necessary to filter and rank market data.
Multi-Factor Strategy Assistant Use Cases
- Creating multi-stage stock screens that combine fundamental data like ROE with technical indicators like Moving Average deviation.
- Developing hybrid investment strategies that weight multiple alpha factors to generate a single composite score for ranking.
- Rapidly prototyping quantitative models by leveraging built-in libraries like WorldQuant Alpha101.
- Generating standardized YAML strategy files for automated trading systems or backtesting engines.
How Multi-Factor Strategy Assistant Works
- Define the strategy objective, specifying the type (Value, Growth, Momentum) and the desired holding period.
- Select specific fundamental and technical factors from the built-in library or define custom mathematical expressions.
- Configure weights for each factor to determine their influence on the final ranking, ensuring the total weight sums to 1.
- Apply normalization methods such as z-score or cross-sectional ranking to make disparate data points comparable.
- Generate a comprehensive YAML configuration file that defines the screening, factor logic, and output parameters.
- Use the quantcli filter run command to execute the strategy against live or historical market data.
Multi-Factor Strategy Assistant Setup
To use this skill effectively, you must have the quantcli tool installed in your environment. Use the following commands to get started:
# Install quantcli from PyPI
pip install quantcli
# Alternatively, install from the source repository
git clone https://gitcode.com/datavoid/quantcli.git
cd quantcli
pip install -e .
# Verify the installation
quantcli --help
Multi-Factor Strategy Assistant Data Schema & Taxonomy
The Multi-Factor Strategy Assistant generates structured YAML files that organize strategy logic into four primary blocks. This structure is essential for Openclaw Skills to interface with quantitative data providers.
| Component | Description | Key Attributes |
|---|---|---|
| screening | Pre-filtering conditions to narrow the stock universe. | fundamental_conditions, daily_conditions, limit |
| factors | The raw indicators used for scoring stocks. | name, expr (mathematical expression), direction, external references |
| ranking | The logic used to fuse multiple factors into a score. | weights (per factor), normalize (zscore/rank) |
| output | Format and constraints for the final result list. | limit, columns (symbol, score, rank) |
Multi-Factor Strategy Assistant Advanced Features
- Integrated support for 40+ WorldQuant Alpha101 factors, allowing for professional-grade reversal and momentum analysis.
- Flexible factor referencing that supports both inline dictionary definitions and external YAML file imports for modular strategy building.
- A rich library of over 40 built-in mathematical functions including rolling_std, rsi, correlation, and cross_up/cross_down detection.
- Advanced cross-sectional normalization techniques like z-score and rank scaling to handle outliers and different data scales effectively.
- Automated validation of screening conditions to prevent empty result sets in overly restrictive strategies.
SKILL.md
Loading
Related Openclaw Skills
ClawdTM Skills API
A specialized API for AI agents and humans to review, rate, and discover the best skills for Claude Code.
Moltbook Curator
A community-driven curation platform where AI agents vote on the most significant Moltbook posts to bridge the gap between AI social activity and human audiences.
swift-mlx-lm
A high-performance Swift framework for running local LLM and Vision-Language Model inference and fine-tuning on Apple Silicon via MLX.
Travel Agent by BonBook
A full-service AI travel agent that manages flight bookings, changes, and cancellations via simple email commands.
ClawPoker
ClawPoker is an agentic AI platform that enables autonomous bots to play Texas Hold'em against one another using a high-availability two-worker architecture.
Johnson & Johnson Business Intelligence
A comprehensive business intelligence skill for analyzing Johnson & Johnson's corporate evolution, financial restructuring, and healthcare market dominance.
Featured*
