← Back to Skills Marketplace
240
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install aigc-risk-assessment
Description
Provides portfolio risk metrics, stress testing, and position management advice using VaR, CVaR, volatility, Beta, Sharpe ratio, and Kelly formula.
README (SKILL.md)
Risk Assessment - 风险评估工具
功能说明
提供投资组合风险评估和仓位管理建议。
核心功能
风险指标
- VaR (风险价值)
- CVaR (条件风险价值)
- 波动率
- Beta 系数
- 夏普比率
压力测试
- 历史情景模拟
- 极端市场测试
- 相关性断裂测试
仓位管理
- 凯利公式
- 风险平价
- 最大仓位建议
使用示例
from risk_assessment import calculate_var, position_suggestion
# 计算 VaR
var_result = calculate_var(stock_code="300308", confidence=0.95)
# 仓位建议
position = position_suggestion(
total_capital=1000000,
risk_tolerance=0.02,
stock_price=534.80,
stop_loss=0.10
)
安装依赖
pip install akshare pandas numpy scipy
Usage Guidance
This appears to be a straightforward risk-assessment helper, but take a few precautions before installing and using it with real capital: (1) Fix or confirm packaging inconsistencies — skill.json exports "stress_test" though no such function exists; ask the author or remove the extra export. (2) Pin dependency versions (pip install akshare==<version>, pandas, numpy, scipy) and audit the akshare package — it performs network requests to fetch market data, so confirm its data sources and trustworthiness. (3) Run the skill in a sandbox or test environment first and validate outputs on known data. (4) Review akshare's upstream code or network behavior if you care about data exfiltration or privacy. (5) If you plan to integrate this with automated agents, consider limiting automatic invocation until you’ve vetted the package. These steps reduce risk; the package itself shows no signs of trying to access unrelated credentials or system resources.
Capability Analysis
Type: OpenClaw Skill
Name: aigc-risk-assessment
Version: 1.0.0
The skill bundle provides standard financial risk assessment and position management tools. The Python code in risk_assessment.py uses legitimate libraries (akshare, pandas, scipy) to fetch public market data and perform statistical calculations without any signs of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The name, description, SKILL.md, and the Python implementation align: the code uses akshare to fetch market data and computes VaR and simple position suggestions. Minor inconsistencies: skill.json exports include "stress_test" which is not implemented in risk_assessment.py, and SKILL.md example uses parameter name "stock_code" while the function signature uses "code". These look like packaging/documentation oversights rather than malicious behavior.
Instruction Scope
SKILL.md only instructs installing dependencies and calling the provided functions. The code performs network calls via the akshare library to fetch market data (expected for a market-risk tool). There are no instructions to read unrelated system files, environment variables, or transmit data to arbitrary endpoints beyond what akshare does.
Install Mechanism
No install spec is provided (instruction-only), and the README suggests pip installing akshare, pandas, numpy, scipy — reasonable for this function. Recommendation: pin dependency versions before installing; review akshare as a third-party package because it performs network I/O.
Credentials
The skill requests no environment variables, credentials, or config paths. That matches its stated purpose and is proportionate.
Persistence & Privilege
always is false and there is no code that modifies other skills or agent-wide configuration. The skill does not request elevated persistence or privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install aigc-risk-assessment - After installation, invoke the skill by name or use
/aigc-risk-assessment - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - Risk assessment tools for financial investments
Metadata
Frequently Asked Questions
What is AI Risk Assessment?
Provides portfolio risk metrics, stress testing, and position management advice using VaR, CVaR, volatility, Beta, Sharpe ratio, and Kelly formula. It is an AI Agent Skill for Claude Code / OpenClaw, with 240 downloads so far.
How do I install AI Risk Assessment?
Run "/install aigc-risk-assessment" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AI Risk Assessment free?
Yes, AI Risk Assessment is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AI Risk Assessment support?
AI Risk Assessment is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AI Risk Assessment?
It is built and maintained by GBABYZS (@gbabyzs); the current version is v1.0.0.
More Skills