← 返回 Skills 市场

All Weather Strategy

Name: All Weather Strategy
Author: wzwangyc

作者 wzwangyc · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

323

总下载

当前安装

版本数

在 OpenClaw 中安装

/install all-weather-strategy

功能描述

Calculate asset allocation weights for a portfolio of ETFs based on Risk Parity (All Weather) principles. Includes annualized return and risk metrics. Fully...

使用说明 (SKILL.md)

All Weather Strategy Skill (Professional Edition)

This skill provides a professional implementation of the Risk Parity (All Weather) investment strategy. It is optimized for the OpenClaw marketplace.

Core Capabilities

Risk Parity Optimization: SLSQP-based solver for equal risk contribution.
Annualized Performance: Forecasts return and volatility based on historical lookback.
Proactive AI Guidance: Instructions optimized for AI agents to interact with humans.

Default Parameters (Standard Config)

Amount: 10,000.0 CNY
Lookback: 365 days
Market Pool: A mix of Global (S&P 500, Nasdaq) and Domestic (STAR 50, Treasury, Gold) ETFs.

AI Interaction Logic

The AI assistant must act as a financial consultant:

Intro: "I can generate an All Weather asset allocation for you."
Options: Offer to use the "Standard Professional Config" or custom settings.
Prompt: Ask specifically about the investment amount and if they want to modify the ETF pool.

Usage Example

from scripts.engine import AllWeatherEngine

# The engine handles all defaults natively
engine = AllWeatherEngine()
results = engine.run()

安全使用建议

This skill appears to do what it says: fetch historical ETF prices, compute risk-parity weights, and produce tables/charts. Before installing, consider: 1) it requires Python libraries (see requirements.txt) and will make network calls to akshare and yfinance to fetch market data — run it in an environment where outgoing network traffic is acceptable; 2) PDF generation may try to register a local Chinese font (simhei.ttf) or fall back to system fonts — the README mentions a resources/ folder but that folder is not present in the provided manifest, so PDF rendering may fall back to defaults; 3) no credentials or secrets are requested, which is appropriate; 4) review and pin dependency versions if you will run this in production, and run in an isolated environment (virtualenv/container) if you want to limit risk from third-party packages. Overall there are no incoherent or suspicious indicators.

功能分析

Type: OpenClaw Skill Name: all-weather-strategy Version: 1.0.0 The skill bundle provides a legitimate financial tool for ETF asset allocation using Risk Parity principles. The implementation in `scripts/engine.py` and `app.py` uses standard libraries (akshare, yfinance, scipy) for data retrieval and optimization, and the instructions in `SKILL.md` are aligned with its stated purpose without any signs of prompt injection or malicious intent. No evidence of data exfiltration, unauthorized execution, or persistence was found.

能力评估

✓ Purpose & Capability

The name/description (All Weather Risk Parity allocator) align with included code: data fetchers (akshare, yfinance), a risk-parity optimizer (scipy minimize SLSQP), metrics calculation, and report generation. The declared requirements (no env vars, no required binaries) match the code's use of Python libraries and no secret/third-party API keys.

ℹ Instruction Scope

SKILL.md instructs the agent to load scripts/engine.py and run engine.run(), and to interactively ask the user for amount/ETF pool — that matches the code. One minor omission: the SKILL.md does not explicitly state that the code will perform network calls to fetch historical prices (via akshare and yfinance) or that a local Chinese font file (simhei.ttf) is optionally used for PDF generation; these are reasonable but worth calling out so users expect network I/O and possible local file access for fonts.

✓ Install Mechanism

There is no install spec (instruction-only install) and dependencies are listed in requirements.txt (akshare, yfinance, numpy, pandas, matplotlib, scipy, reportlab, streamlit, altair) — these are consistent with the code. No downloads from arbitrary URLs or archive extraction are present in the manifest.

✓ Credentials

The skill requests no environment variables, credentials, or config paths. The code performs network requests to public data providers (akshare/yfinance) but does not attempt to read secrets or unrelated system files.

✓ Persistence & Privilege

The skill is not always-enabled and does not modify other skills or system-wide settings. It generates files (CSV/PDF) when asked, but does not request persistent elevated privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install all-weather-strategy
安装完成后，直接呼叫该 Skill 的名称或使用 /all-weather-strategy 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the All Weather Strategy skill (Professional Edition) - Calculates ETF portfolio weights based on Risk Parity (All Weather) principles - Provides annualized return and risk estimates using historical data - Features default settings with global and domestic ETF pool and CNY support - Includes proactive AI-guided interactions for portfolio customization and advice

元数据

Slug all-weather-strategy

版本 1.0.0

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 1

常见问题