Portfolio Optimization

提供多策略投资组合优化框架，支持均值-方差、Black-Litterman 和分层风险平价（HRP）算法，内置多种协方差估计方法对比分析。

This skill appears to be a legitimate portfolio-optimization blueprint, but its runtime instructions ask the agent to run environment checks and potentially install packages and write files on your host. Before installing or running it: 1) Inspect references/seed.yaml and SKILL.md yourself to confirm you accept the described execution protocol. 2) Run the skill in an isolated environment (dedicated VM or container) so its pip installs and data recorders cannot affect your main system. 3) Be prepared to supply any data-provider credentials manually; the skill does not declare them but will interact with providers like eastmoney/joinquant and may attempt network fetches. 4) If you don’t want the agent to auto-install packages, deny or review any pip install steps and perform installs manually after vetting package sources (verify zvt package origin and version). 5) Confirm you are comfortable with the semantic locks and fatal preconditions (e.g., next‑bar execution, T+1 rule) because they enforce strict behavior that can halt runs. If you want higher assurance, ask the author for an explicit install recipe, a minimal runtime manifest (declared env vars like ZVT_HOME), and signed package sources before use.

Type: OpenClaw Skill Name: portfolio-optimization Version: 0.3.3 The portfolio-optimization skill bundle is a highly structured framework for financial analytics using the zvt library. It contains extensive safety documentation, including 14 anti-patterns (references/ANTI_PATTERNS.md) and 43 fatal constraints (references/seed.yaml) designed to prevent common quantitative trading errors like look-ahead bias and numerical instability. The shell commands in the preconditions (PC-01 to PC-04) are limited to environment validation and directory permission checks, and the instructions for the AI agent are focused on enforcing code quality and regulatory compliance rather than unauthorized actions.