← Back to Skills Marketplace
212
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install statistical-arbitrage
Description
統計套利(配對交易)專業策略 - 計算動態對沖比率、執行回測並生成完整報告。 支持港股(.HK)、美股(無後綴或預設)、A股(.SS/.SZ)等多市場。 Use when: 用戶說「分析統計套利策略」、「幫我回測AAPL和GOOGL」、「配對交易回測」。 NOT for: 單股票分析、趨勢交易、期貨套利、股票掃描。
Usage Guidance
Do not assume the skill will behave as the README/SKILL.md claims. Specific issues to consider before installing or running:
- The included Python script is labelled 'Obfuscated Version', uses non-descriptive variable names, and hardcodes defaults (tickers, train/test split, and an output path variable). That makes auditing harder. Ask the author for a clear, non-obfuscated version.
- SKILL.md and package.json advertise CLI options and many output files (PNG, report.html, CSV). The script does not parse command-line arguments nor save plots or CSV/HTML outputs — it only prints summaries. If you need the promised outputs, request a corrected script that implements argument parsing and file-generation.
- The script contains a hardcoded path ('/Users/houloi/Desktop/代碼/') which could be used to write files to that location if later code uses it; confirm whether the script will write anywhere and where. Prefer explicit --output handling and safe default in the current working directory.
- Because the code runs network calls (yfinance), run it in a controlled environment or sandbox first to inspect actual network activity and produced files.
- If you plan to use this for trading decisions, validate results independently (the README includes appropriate risk warnings). Consider requesting unit tests or example outputs that match the documentation.
If the author provides a non-obfuscated, argument-parsing version that actually writes the claimed outputs (or SKILL.md is corrected to match code), re-evaluate; until then treat the skill as untrusted for automation.
Capability Analysis
Type: OpenClaw Skill
Name: statistical-arbitrage
Version: 1.0.4
The skill bundle is classified as suspicious primarily due to heavy obfuscation of the main logic in 'scripts/statistical_arbitrage.py', which directly contradicts the 'open source and auditable' claim made in the 'SKILL.md' documentation. There is also a significant discrepancy between the documented capabilities (which describe a command-line interface generating PNG and HTML reports) and the actual code, which uses hardcoded parameters and only outputs to the console. Additionally, the script contains a hardcoded local file path ('/Users/houloi/Desktop/代碼/'), suggesting it may be a poorly repurposed or deceptive script.
Capability Assessment
Purpose & Capability
Name/description promise a full pairs-trading backtester that accepts user-specified tickers/periods and writes plots/HTML/CSVs. The package only requires python3 (reasonable), but the shipped code uses hardcoded default tickers/dates and a hardcoded output path variable; that does not align with the stated interactive/parameterized capability.
Instruction Scope
SKILL.md instructs installing dependencies and running the script with --stock1/--stock2/--start/--end/--output etc. The actual script contains no argument parsing (it ignores CLI args and uses internal defaults), and it prints summaries rather than producing the many PNG/HTML/CSV files the doc claims. That is a substantive scope discrepancy — the instructions would cause the agent to expect generated files that the code does not produce.
Install Mechanism
No remote download/install is performed; dependencies are standard Python packages installed via pip (yfinance, pandas, numpy, statsmodels, matplotlib). An install script is included that runs pip; this is expected and proportionate for the declared functionality.
Credentials
The skill requests no environment variables or credentials. Dependencies access only public Yahoo Finance via yfinance which matches the stated data source. No secrets or unrelated credentials are requested.
Persistence & Privilege
The skill is not always-included and does not request elevated persistence. The install script writes a local test_config.json and may create files if run, which is normal for a local analysis tool; nothing modifies other skills or global configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install statistical-arbitrage - After installation, invoke the skill by name or use
/statistical-arbitrage - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- Removed internal metadata files: `.clawhub/origin.json` and `_meta.json`.
- No functional or user-facing changes in logic or documentation.
v1.0.3
- 修正報告生成部分,原先支援 Excel 匯出,現統一為 CSV 格式導出。
- 範例、流程描述及 troubleshooting 命令微調,與現有功能保持一致。
- 版本號升級為 1.0.3,無其他功能/邏輯變更。
v1.0.2
- 停止支持股票池/行業自動掃描和配對功能;本版本僅專注於單一股票對的統計套利分析。
- 移除掃描相關文件與文檔說明,並在觸發條件中特別排除「股票掃描」用途。
- 新增內部配置文件 .clawhub/origin.json,移除舊 pair_scanner 腳本。
- 文檔描述聚焦於雙股票配對分析、動態對沖比率計算與回測,刪除「股票池掃描」相關舉例與流程。
v1.0.1
v1.0.1
修復字體兼容性問題(移除 SimHei)
改進跨平台字體支持
修正 package.json 配置(Python runtime)
vv1.0.1
## v1.0.1 - 修復字體兼容性問題(移除 SimHei) - 改進跨平台字體支持 - 修正 package.json 配置(Python runtime)
v1.0.0
statistical-arbitrage v1.0.0
- Initial release of professional statistical arbitrage (pair trading) strategy analysis.
- Automatic cointegration testing, dynamic hedge ratio calculation, backtesting, and detailed reporting.
- Supports Hong Kong, US, and China A-shares (with stock code suffix recognition).
- Generates 6 types of charts, HTML interactive report, and Excel exports.
- Configurable entry/exit/stop thresholds with robust error handling and troubleshooting guidance.
- Intended for pair trading analysis and multi-market scanning; not for single-stock, futures, or crypto analysis.
Metadata
Frequently Asked Questions
What is Statistical Arbitrage 統計套利?
統計套利(配對交易)專業策略 - 計算動態對沖比率、執行回測並生成完整報告。 支持港股(.HK)、美股(無後綴或預設)、A股(.SS/.SZ)等多市場。 Use when: 用戶說「分析統計套利策略」、「幫我回測AAPL和GOOGL」、「配對交易回測」。 NOT for: 單股票分析、趨勢交易、期貨套利、股票掃描。 It is an AI Agent Skill for Claude Code / OpenClaw, with 212 downloads so far.
How do I install Statistical Arbitrage 統計套利?
Run "/install statistical-arbitrage" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Statistical Arbitrage 統計套利 free?
Yes, Statistical Arbitrage 統計套利 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Statistical Arbitrage 統計套利 support?
Statistical Arbitrage 統計套利 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Statistical Arbitrage 統計套利?
It is built and maintained by Loi214 (@loi214); the current version is v1.0.4.
More Skills