量化交易知识
v1.0.0量化交易知识与技能。包括多因子选股、技术指标、经典策略(双均线、网格交易、突破策略)、套利策略、回测框架(Backtrader)、风险指标等。用于回答量化交易相关问题、股票分析、策略建议等。
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name and description (quant trading knowledge, strategies, backtesting, risk metrics) align with the provided instructions and reference files. All declared content (strategy templates, indicators, data sources) matches the stated purpose; there are no unrelated requirements (no unexpected env vars, binaries, or config paths).
Instruction Scope
SKILL.md and references contain only educational content, analysis templates, and strategy pseudocode. The instructions do not tell the agent to read local files, access system credentials, or transmit data to unknown endpoints. They only mention common public data sources (eastmoney.com, exchanges) and typical trading interfaces (QMT/掘金) in context, which is appropriate for the skill's purpose.
Install Mechanism
There is no install specification and no code files to write or execute. Being instruction-only minimizes disk/write risk and there are no download URLs or package installs to evaluate.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate for a knowledge/education skill. Note: if the skill were later extended to connect to brokers or data APIs, credentials would then be expected and should be scoped minimally.
Persistence & Privilege
always is false and the skill does not request elevated or persistent system privileges. It does not modify other skills or system-wide settings; autonomous invocation is enabled (platform default) but that is expected for skills and not by itself a concern here.
Assessment
This skill is an informational, instruction-only skill focused on quantitative trading and appears coherent and low-risk as delivered. Before using it for live trading: (1) do not provide any broker/API credentials unless you verify a legitimate, documented integration and that credentials are scoped (read-only vs trading); (2) treat strategy suggestions as educational — backtest with your own data including fees, slippage, and realistic execution constraints; (3) verify any real-time data sources the agent uses and confirm the agent/platform’s network access policies; (4) if the skill is later updated to include downloads, install scripts, or requests for environment variables, re-evaluate (such changes would raise risk); (5) consider regulatory/compliance requirements for automated trading in your jurisdiction and avoid running strategies with real money until thoroughly tested.Like a lobster shell, security has layers — review code before you run it.
latest
量化交易技能
本技能提供量化交易核心知识,用于股票分析、策略建议、量化学习指导。
核心能力
- 股票分析 - 基本面+技术面分析,给出买入/卖出建议
- 选股建议 - 根据多因子模型筛选优质股票
- 策略知识 - 双均线、网格交易、突破策略、动量策略等
- 风险控制 - 仓位管理、止损止盈
常用指标
基本面
- PE(市盈率)、PB(市净率)
- ROE(净资产收益率)
- 净利润增长率
- 股息率
技术面
- MA(均线)、EMA(指数移动平均)
- RSI(相对强弱指标)
- MACD(平滑异同移动平均线)
- KDJ、OBV
- 布林带(Bollinger Bands)
买入建议模板
当分析股票时,使用以下模板:
## 📊 [股票名称] ([代码]) 分析
### 当前行情
- 当前价:[X]元
- 涨跌幅:[X]%
- 总市值:[X]亿
### 基本面分析
| 指标 | 数值 | 评价 |
|------|------|------|
| PE | X | |
| PB | X | |
| ROE | X% | |
| 净利润增长 | X% | |
### 建议
- 建议买入价:X-X元
- 止损价:X元(-X%)
- 目标价:X元(+X%)
- 仓位建议:X%
数据来源
- 实时行情:东方财富网 (eastmoney.com)
- 公告/研报:交易所官网、券商研报
学习路线
如需学习量化交易,参考:
- Python基础(Pandas、NumPy)
- 金融基础知识
- 技术指标
- 经典策略实现
- Backtrader回测
- 实盘接口(QMT/掘金)
详细知识见 references/ 目录。
Comments
Loading comments...
