QuantML-ResearchQuantML-ResearchOfficialยท1 Agent Skills Included

wq-alpha-research

WorldQuant BRAIN alpha design, backtesting, and submission automation

Designs WorldQuant BRAIN alpha expressions, searches 4,367 local data fields, and diagnoses simulation failures like low Sharpe or high turnover. Checks daily-return correlation against existing alphas before submission to avoid duplicates. Automates backtests, submissions, and status verification, then distills each run into reusable research rules.
npx skills add QuantML-Research/wq-alpha-research --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install wq-alpha-research?โ–ผ

Run `npx skills add QuantML-Research/wq-alpha-research --all -g -y` in your terminal to install this skill globally.

How to find valid WorldQuant BRAIN data fields?โ–ผ

Search the built-in local snapshot of 4,367 USA TOP3000 delay=1 fields by keyword or category, then verify candidates with a simple rank(field) simulation.

How to avoid self-correlation failures on BRAIN?โ–ผ

Compare your new alpha's daily PnL returns against all ACTIVE alphas and keep the correlation below 0.7 before submitting.

Does it work with Claude Code and other agents?โ–ผ

Yes. It follows the universal SKILL.md standard and runs in Claude Code, Cursor, Codex, and other compatible agents.

Do I need a WorldQuant BRAIN account?โ–ผ

Yes. Provide your credentials via the WQ_BRAIN_USERNAME and WQ_BRAIN_PASSWORD environment variables; they are never committed to the repository.

Related Repositories in Finance & Accounting

View All in Finance & Accountingโ†’