Rqalpha Cn Backtest

基于20日价格动量在沪深300、沪深500与国债之间自动轮转配置，通过RQAlpha框架执行完整回测并评估组合绩效。

This skill appears coherent with a backtesting helper, but there are important mismatches you should address before installing or granting the agent permission to run it: - Expect the agent to run Python commands and possibly pip install packages (e.g., zvt). Run these installs yourself in a controlled environment (virtualenv/container) rather than letting the agent run them automatically. - The skill references ZVT_HOME (~/.zvt) and will attempt to write there as a precondition test; ensure you are comfortable with that path and permissions or set ZVT_HOME to an isolated directory. - If you plan to use paid data providers (joinquant, brokers), the skill will need credentials — the package manifest does not declare these env vars. Do not paste credentials into a conversation; prefer configuring them in the host's secret store and only grant minimal-scoped tokens. - Ask the publisher for a concrete install spec and a list of required env vars (jqdatasdk tokens, broker API keys) and for a minimal reproducible example of the exact shell/python commands the agent will run. The current mismatch (no install spec vs SKILL.md that runs installs) is the main reason this is flagged suspicious. If you want to proceed safely: run the skill locally inside an isolated VM/container, manually perform and inspect the prereq installs, set ZVT_HOME to a disposable directory, and do not provide credentials until you confirm what calls will be made and where data will be transmitted.

Type: OpenClaw Skill Name: rqalpha-cn-backtest Version: 0.3.3 The bundle is a highly structured configuration for a quantitative trading assistant focused on the A-share market using the zvt and rqalpha frameworks. It contains extensive domain-specific knowledge, including 25 anti-patterns (ANTI_PATTERNS.md), market-specific constraints (CONSTRAINTS.md), and semantic locks (LOCKS.md) designed to prevent common backtesting errors like look-ahead bias and T+1 settlement violations. The execution protocols in seed.yaml are complex but strictly aligned with the stated purpose of providing a safe, rule-bound environment for generating financial code. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.