Vectorbt Vectorized

基于 VectorBT 框架的向量化回测与因子研究工具，支持多市场数据批量回测、策略参数优化和统计套利分析。

This skill appears to be a detailed, local 'crystal' for vectorized backtesting (vectorbt/ZVT) and is instruction-only (no code files to run from the registry). Before installing or running it: 1) ask the author/vendor for a short, explicit runtime manifest: which Python version, which pip packages (exact names/versions), and whether network/pip access is required; 2) verify whether it will run pip installs or create/modify local directories (SKILL.md references ZVT_HOME and pip install in preconditions); 3) run it in a sandboxed environment (container / disposable VM) the first time so package installation and any filesystem changes don't affect your primary workstation; 4) confirm the provenance/license (source unknown, license marked Proprietary); 5) if you need to run it on a shared system, ensure you have explicit permission for network installs and that no secrets or external webhooks will be used by the skill. If the author provides a clear, minimal dependency list and trusted install sources (PyPI package names or GitHub releases), this would reduce the concern.

Type: OpenClaw Skill Name: vectorbt-vectorized Version: 0.3.3 The bundle is a comprehensive quantitative finance toolset for backtesting and factor research based on the VectorBT and ZVT frameworks. It contains an extensive library of 'anti-patterns' and 'semantic locks' (e.g., in SKILL.md and seed.yaml) specifically designed to prevent common financial modeling errors such as look-ahead bias, survivorship bias, and data leakage. The instructions for the AI agent are strictly aligned with its role as a financial assistant, and the shell commands in the preconditions are limited to standard environment and dependency checks. No evidence of data exfiltration, malicious persistence, or harmful prompt injection was found.