Chanlun Pattern Recognition
HKUDS/Vibe-Trading
Detects Chan theory price structures (fractals, strokes, pivots) and first, second and third buy and sell points from OHLCV bars using the czsc library, in Chinese.
Chinese-language playbook for WorldQuant BRAIN alphas: choose fields, write expressions, backtest, diagnose check failures, tune turnover, submit and build portfolios.
SKILL.md written in Chinese; this summary is our English description.
Install WorldQuant BRAIN Alpha Research
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-research --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .claude/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .agents/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .cursor/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .gemini/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-researchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .github/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install QuantML-Research/wq-alpha-research wq-alpha-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "wq-alpha-research" agent skill from https://github.com/QuantML-Research/wq-alpha-research/tree/main into .opencode/skills/wq-alpha-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wq-alpha-research", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
wq-alpha-research- GitHub stars
- 405
- Token cost
- ~4.9k tokens
- SKILL.md length
- 738 words
- Files
- 10 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Chinese-language playbook for WorldQuant BRAIN alphas: choose fields, write expressions, backtest, diagnose check failures, tune turnover, submit and build portfolios.
- Works in 12 steps: 快速决策树 → 字段速查（本地数据集） → 运算符速查表 → …
- Designing a new WorldQuant BRAIN alpha expression
- SKILL.md covers 1. 快速决策树, 2. 字段速查（本地数据集）, 3. 运算符速查表 and 4. 因子模板库, plus 6 more sections
- Runs Python scripts from its folder; calls pyenv; reaches api.worldquantbrain.com; needs WQ_BRAIN_PASSWORD
What it does
A playbook that runs from fields to expressions, backtests, checks, submission and portfolio building for WorldQuant BRAIN alphas, written mostly in Chinese. It opens with a quick decision tree, for example reviewing only ACTIVE alphas and changing or dropping one whose daily-return correlation with the others is above 0.7.
It ships a local copy of the field list for the USA TOP3000 universe at delay 1, with 4367 fields as JSON, CSV and a summary file, grouped into fundamental, analyst, news, price-volume, option, model and social media categories, so fields need not be fetched each time. A refetch is only needed for another region, universe or delay. An operator cheat sheet groups functions into cross-sectional, time-series, group, conditional and vector types, and a template library and recommended default settings for decay, neutralization, truncation and NaN handling complete the guide. A script named evolve_skill.py is also included.
When your agent uses it
- Designing a new WorldQuant BRAIN alpha expression
- Diagnosing why an alpha fails simulation or in-sample checks
- Tuning Sharpe, fitness or turnover before submitting
- Building a set of low-correlation alphas
Example prompts
- “Design an ROE trend alpha for USA TOP3000 and suggest simulation settings.”
- “My alpha fails the turnover check; how can I lower it?”
- “Find fundamental fields I can use for a quality factor.”
- “Review my active alphas and pick which ones to drop for correlation.”
Requirements
- Access to the WorldQuant BRAIN platform
- Python, for the local field-search snippets and scripts
Workflow steps
12 steps, taken from the step headings in SKILL.md.
- 快速决策树
- 字段速查（本地数据集）
- 运算符速查表
- 因子模板库
- 指标与检查
- 问题诊断与修复
- BRAIN API 自动化
- 组合构建规则
- 提交前 Checklist
- 核心经验（一句话版）
- 自进化机制
- 实证记录（自动更新）
What it can do on your machine
Read from SKILL.md and the folder at commit 86d7531. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pyenv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.worldquantbrain.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
WQ_BRAIN_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
WorldQuant BRAIN Alpha Research loads about 4.9k tokens when it runs, and up to ~1.1M if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 738 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 738 words (~4,902 tokens).
“本 SKILL 已内置 USA TOP3000 delay=1 的完整字段列表（共 4367 个），无需每次从网页/ API 拉取：”
- name
- wq-alpha-research
Files
SKILL.md and 9 other files (scripts, references) in the repository root of QuantML-Research/wq-alpha-research.
- SKILL.md
- .gitignore
- README.md
- pic/20260624124943.jpg
- pic/20260624125220.jpg
- pic/20260626094115.png
- references/wq_usa_top3000_delay1_data_fields.csv
- references/wq_usa_top3000_delay1_data_fields.json
- references/wq_usa_top3000_delay1_data_fields_summary.json
- scripts/evolve_skill.py
Open the folder on GitHubat commit 86d7531
Compare with similar skills
WorldQuant BRAIN Alpha Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| WorldQuant BRAIN Alpha Research this skillQuantML-Research/wq-alpha-research | 405 | — | ~4.9k | Automated safety check: Pass | None | |
| Chanlun Pattern RecognitionHKUDS/Vibe-Trading | 35k | — | ~658 | Automated safety check: Pass | MIT | |
| Elliott Wave Signal EngineHKUDS/Vibe-Trading | 35k | — | ~482 | Automated safety check: Pass | MIT | |
| yfinance Market DataHKUDS/Vibe-Trading | 35k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Candlestick Pattern SignalsHKUDS/Vibe-Trading | 35k | — | ~468 | Automated safety check: Pass | MIT | |
| Ichimoku Kinko Hyo SignalsHKUDS/Vibe-Trading | 35k | — | ~417 | Automated safety check: Pass | MIT |
Similar skills
Elliott Wave Signal Engine
HKUDS/Vibe-Trading
Detects Elliott Wave structures in price data with a Zigzag swing finder and Fibonacci checks, and turns completed waves into long, short or flat signals.
yfinance Market Data
HKUDS/Vibe-Trading
Pulls price history and company research data for US, Hong Kong and Canadian stocks, ETFs and indices from Yahoo Finance, with no API key.
Candlestick Pattern Signals
HKUDS/Vibe-Trading
Detects 15 classic candlestick patterns with vectorized pandas code and combines bullish and bearish scores into a long, short or flat trading signal.
Ichimoku Kinko Hyo Signals
HKUDS/Vibe-Trading
Generates trading signals from the Ichimoku five-line system using Tenkan and Kijun crossovers, cloud position and cloud direction, implemented in pandas.
Minute-Level Data and Backtesting
HKUDS/Vibe-Trading
Fetches minute candlesticks from OKX, Tushare or yfinance, computes intraday VWAP, TWAP and volume distribution, and runs minute-level backtests by setting an interval in config.json.
Related
Works with
Categories
Questions about WorldQuant BRAIN Alpha Research
What does WorldQuant BRAIN Alpha Research do?
Chinese-language playbook for WorldQuant BRAIN alphas: choose fields, write expressions, backtest, diagnose check failures, tune turnover, submit and build portfolios. A playbook that runs from fields to expressions, backtests, checks, submission and portfolio building for WorldQuant BRAIN alphas, written mostly in Chinese.7.
When should I use WorldQuant BRAIN Alpha Research?
WorldQuant BRAIN Alpha Research fits situations like: designing a new WorldQuant BRAIN alpha expression; diagnosing why an alpha fails simulation or in-sample checks; tuning Sharpe, fitness or turnover before submitting; building a set of low-correlation alphas.
How do I install WorldQuant BRAIN Alpha Research in Claude Code?
Run `npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a claude-code`. Or copy the skill folder (the QuantML-Research/wq-alpha-research repository) into .claude/skills/wq-alpha-research in your project. Claude Code loads it when a task matches its description.
How do I install WorldQuant BRAIN Alpha Research in Codex?
Run `npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a codex`. Or copy the skill folder (the QuantML-Research/wq-alpha-research repository) into .agents/skills/wq-alpha-research in your project. Codex loads it when a task matches its description.
Can I use WorldQuant BRAIN Alpha Research in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QuantML-Research/wq-alpha-research --skill wq-alpha-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wq-alpha-research, .gemini/skills/wq-alpha-research, .github/skills/wq-alpha-research and .opencode/skills/wq-alpha-research in your project.
What does WorldQuant BRAIN Alpha Research need to run?
Going by SKILL.md and its folder, WorldQuant BRAIN Alpha Research needs Python for the scripts in its folder, the command-line tools its instructions call (pyenv) and credentials named WQ_BRAIN_PASSWORD. Our summary lists: Access to the WorldQuant BRAIN platform; Python, for the local field-search snippets and scripts.
Does WorldQuant BRAIN Alpha Research access the network?
SKILL.md names 1 domain. In commands or code: api.worldquantbrain.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is WorldQuant BRAIN Alpha Research safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does WorldQuant BRAIN Alpha Research use?
No licence was found for WorldQuant BRAIN Alpha Research or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does WorldQuant BRAIN Alpha Research use?
About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1M tokens, read only when the agent opens those files.
What are the alternatives to WorldQuant BRAIN Alpha Research?
Skills that share tags, products or a category with WorldQuant BRAIN Alpha Research: Chanlun Pattern Recognition (HKUDS/Vibe-Trading, 35k stars), Elliott Wave Signal Engine (HKUDS/Vibe-Trading, 35k stars), yfinance Market Data (HKUDS/Vibe-Trading, 35k stars) and Candlestick Pattern Signals (HKUDS/Vibe-Trading, 35k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains WorldQuant BRAIN Alpha Research?
QuantML-Research (a GitHub organization) maintains it in QuantML-Research/wq-alpha-research, which has 405 GitHub stars. The repository was last updated on June 29, 2026.
Source: QuantML-Research/wq-alpha-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.