Quant Strategy

辅助编写和回测量化交易策略，支持因子分析

Security Scan

The skill's instructions and requirements are consistent with a quant-strategy helper: it only contains guidance for producing Python backtest/ factor-analysis code and requests no installs, credentials, or file access.

Purpose & Capability

Name/description: 'Quant Strategy' — SKILL.md instructs the agent to help design factors, write Python strategies, process data, run/interpret backtests and suggest optimizations. There are no declared binaries, env vars, or config paths that would be unexpected for this purpose.

Instruction Scope

Instructions stay within the stated domain (strategy design, code examples, metrics). The skill does not instruct the agent to read local files, access system paths, or exfiltrate data. Note: the skill may sensibly recommend using market-data or broker APIs (which typically require credentials) but it does not request or handle any secrets itself.

Install Mechanism

No install spec and no code files — instruction-only skill. This is low-risk because nothing is written to disk by the skill package itself.

Credentials

The skill declares no required environment variables, credentials, or config paths. That matches the instruction-only nature and the described functionality.

Persistence & Privilege

always:false and default invocation settings. The skill does not request permanent presence or modification of other skill/system configurations.

Assessment

This skill appears coherent and instruction-only, so it doesn't demand credentials or install anything. Before using: (1) review any code the assistant generates before executing it (especially if it performs network I/O or system calls); (2) never paste API keys, broker credentials, or other secrets into chats — if you connect to data/broker APIs later, use secure credential storage; (3) be aware backtest results are not guarantees of live performance and validate strategies in a sandbox or paper-trading environment; (4) note the skill metadata restricts OS to win32, but since it's instruction-only that mostly affects any platform-specific advice the assistant might give.

量化策略助手

你是一个量化交易策略助手，帮助用户构建和优化量化投资策略。

能力

1. 因子构建：帮助设计和实现各类选股因子，包括价值因子、成长因子、动量因子、质量因子、波动率因子等。

2. 策略编写：用 Python 编写量化交易策略代码，支持常见回测框架（如 backtrader、vnpy、聚宽等）。

3. 数据处理：协助处理股票行情数据、财务数据的清洗、转换和特征工程。

4. 回测分析：分析策略回测结果，包括年化收益率、最大回撤、夏普比率、胜率等关键指标。

5. 策略优化：提供策略改进建议，包括参数优化、风控规则设计、仓位管理等。

注意事项

• 回测结果不代表实盘表现
• 需要注意过拟合风险
• 交易成本（手续费、滑点）对策略表现有重要影响
• 建议在模拟盘验证后再考虑实盘