ClawHub

Quant Strategy Development

v1.0.0

量化策略开发主技能。当用户说"开发量化策略"、"设计量化策略"、"写策略代码"、"量化策略开发"时自动触发。提供标准开发流程、代码规范、检查清单、代码模板。适用于量化策略项目的开发阶段。

⭐ 1· 159·1 current·1 all-time
by@xueylee-dotcom
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (quant strategy development) match the SKILL.md content: design process, code templates, testing and backtest/real-trade checklists. The skill does not request unrelated binaries, cloud credentials, or system access.
✓
Instruction Scope
SKILL.md contains coding patterns, test templates, backtest and live-trade checklists and explicit warnings about testing and risk controls. It does not instruct reading arbitrary system files, exfiltrating data, or contacting hidden endpoints. It references trading APIs (QMT) and order calls (passorder) which are expected for this domain.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files to run; nothing is written to disk and no remote downloads are performed.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. While the guidance assumes eventual connection to trading/broker APIs (which will require credentials), the skill itself does not request or handle secrets — this is proportionate for a documentation/template skill.
✓
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent or elevated privileges or modify other skills' configs. Autonomous invocation is allowed by platform default and is not combined with other red flags.
Assessment
This skill is a documentation/template pack for building trading strategies and appears internally consistent. Before using any generated or copy-pasted code: 1) review any order-sending calls (e.g., passorder) and ensure they point to test/sandbox endpoints; 2) never supply broker/API credentials to the skill itself unless you trust the runtime environment; 3) run extensive unit/backtests and perform small-sum live tests as the skill advises; 4) audit any integrated code you add for safety (rate limits, anti-self-trading checks, hard-coded limits) because executing trading code can cause real financial loss.

Like a lobster shell, security has layers — review code before you run it.

latestvk9750e8s6g8cwta2r0wc65ajzd83qvzr

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments