QMT Development
v1.0.0QMT平台开发专用技能。当用户说"QMT"、"实盘"、"QMT策略"、"QMT回测"、"QMT开发"时自动触发。提供QMT API规范、核心函数机制、止损监控方式、实盘注意事项。适用于使用QMT平台的量化策略开发。
⭐ 0· 135·0 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
The skill is a documentation/instruction-only skill for developing strategies on the QMT platform. It does not request unrelated environment variables, binaries, or installs, and the examples (order calls, stop-loss checks, reading local signal files) match the declared purpose.
Instruction Scope
SKILL.md contains concrete code templates that read local files (e.g., trading_signals/alphagbm_signals_qmt.json) and demonstrate calling trading functions (passorder, get_trade_detail_data). Those are appropriate for a QMT dev guide, but they imply the runtime agent or user environment will have access to local project files and platform APIs; users should be aware the examples assume access to trading account identifiers and platform APIs.
Install Mechanism
No install spec and no code files are included, so nothing will be downloaded or written to disk by the skill itself—this is the lowest-risk install profile.
Credentials
The skill does not request environment variables or credentials. However, its code samples use accID and platform order functions; if the agent environment supplies trading credentials, the agent could interact with live accounts. That is expected for a trading dev guide but worth noting as a security consideration.
Persistence & Privilege
always is false and there is no persistent install; the skill does not request elevated persistence or modify other skills or system-wide settings.
Assessment
This skill is a documentation-only QMT development guide and appears coherent with its purpose. Before enabling it in an agent that can act autonomously, confirm whether the agent runtime has access to any trading account credentials or local signal files — if so, the agent could place live orders if given permission. If you only want help drafting or reviewing code, keep the agent's ability to call external trading APIs or access account credentials disabled; if you intend the agent to execute trades, limit it to a test/sandbox account and review the code templates and waiting_list/anti-duplication logic carefully.Like a lobster shell, security has layers — review code before you run it.
latestvk978r2wtgtm6r6avdn38kpceqx83p537
License
MIT-0
Free to use, modify, and redistribute. No attribution required.