A Share Overnight Trading
v1.0.0A股主板隔夜交易法选股策略。当用户需要每日尾盘在A股主板（60开头沪市、00开头深市主板）中选一支股票进行隔夜交易（今日尾盘买入，次日开盘卖出）时使用此技能。包含筛选标准、操作流程、风险控制和执行纪律。适用于追求隔夜价差的短线交易者。
⭐ 0· 69·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, reference docs and the included Python scripts (backtest, quick check, position calculator) are consistent: all are focused on selecting, sizing and backtesting A‑share overnight trades. There are no unrelated required env vars, binaries, or config paths.
Instruction Scope
SKILL.md gives a manual workflow (board/stock selection, timing, risk rules) and references the included helper scripts. The instructions do not direct reading of unrelated system files or transmission of data to unexpected endpoints. The scripts use mocked data and explicitly note where a user could add real data sources.
Install Mechanism
The skill is instruction-only (no platform install spec) but ships Python scripts that import pandas, numpy, matplotlib and reference optional data providers (tushare/akshare). Those dependencies are not declared in registry metadata — users must install them from PyPI and if they wire real data providers they will need provider SDKs and tokens. This is standard for analysis code but worth noting because running the scripts requires installing third‑party packages.
Credentials
The skill requests no environment variables, credentials, or config paths. The only potential sensitive requirement would be if a user modifies scripts to use external data APIs (tushare/akshare), in which case API keys would be needed — but the shipped code does not hardcode or demand any secrets.
Persistence & Privilege
Skill is not always-on and does not request elevated or persistent platform privileges. It does not modify other skills or system-wide configs.
Assessment
This skill appears internally consistent and focused on an overnight A‑share trading method. Before using: (1) treat it as educational, not investment advice; backtest with real historical data before risking capital; (2) running the provided scripts requires installing Python packages (pandas, numpy, matplotlib) — install from official sources; (3) if you connect the scripts to real data providers (tushare/akshare) you will need API keys — store those securely and audit any code you add to ensure it doesn't transmit keys elsewhere; (4) run code in a controlled environment (virtualenv / container) if you are unsure; and (5) verify any modifications (especially network calls) before using with live trading or real funds.Like a lobster shell, security has layers — review code before you run it.
latestvk975kpacs5wgftzqy0qnzsgs0h83z8ac
License
MIT-0
Free to use, modify, and redistribute. No attribution required.