A股多策略组合/策略配置分析
SkillDev toolsThis skill lets your AI analyze how multiple A-share strategies work together as one portfolio. Ask whether your strategies overlap, how they complement each other, or how to spread allocations across them, and it will give a quantitative answer built on cn-stock-data. You can choose a formal research-report style or a brief quick analysis.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, ask a question like 'how should I combine these strategies' or 'what is the correlation between my strategies'. Mention whether you want a full report or a quick summary.
Then ask your AI: use the A股多策略组合/策略配置分析 skill
What your AI can do with it
- Quantify the synergy between strategies in a combined A-share portfolio
- Measure correlation between strategies to spot overlap or diversification
- Help decide how to allocate across a set of strategies
- Pull the underlying market data from cn-stock-data
- Answer in a formal research-report style or a brief quick-analysis style
What this skill tells your AI
The instructions your AI receives, as published by aifinlab/finclaw in skills/a-share-multi-strategy/SKILL.md and read by ahel’s review.
数据源
SCRIPTS="$SKILLS_ROOT/cn-stock-data/scripts"
python "$SCRIPTS/cn_stock_data.py" kline --code [CODE] --freq daily --start [日期]
python "$SCRIPTS/cn_stock_data.py" quote --code [CODE]
python "$SCRIPTS/cn_stock_data.py" finance --code [CODE]
Workflow
Step 1: 策略池定义
列出候选策略（动量/价值/均值回归/事件驱动等），明确各策略逻辑。
Step 2: 单策略回测
分别回测各策略的收益率序列、夏普比率、最大回撤。
Step 3: 策略相关性分析
计算策略间收益率相关矩阵，识别低相关/负相关策略组合。
Step 4: 策略权重优化
- 等权配置
- 风险平价（按波动率倒数加权）
- 最大夏普比率优化
- 最小相关性组合
Step 5: 输出
| 维度 | formal | brief |
|---|---|---|
| 策略表现 | 各策略完整回测 | 夏普/回撤 |
| 相关矩阵 | 完整相关性热力图 | 平均相关系数 |
| 组合效果 | 多种配置方案对比 | 推荐配置 |
默认风格：brief。
关键规则
- 低相关性策略组合才有分散化价值
- 策略相关性在极端行情下会趋同（尾部相关性上升）
- A 股策略容量有限——小盘策略尤其需要考虑冲击成本
- 定期再平衡（月度/季度）优于漂移不管
- 策略失效检测：滚动夏普比率跌破阈值时降权
使用示例
示例 1: 基本使用
# 调用 skill
result = run_skill({
"param1": "value1",
"param2": "value2"
})
示例 2: 命令行使用
python scripts/run_skill.py --input data.json
Signals
- GitHub stars
- 241
- Forks
- 38
- Last commit
- May 2026
Advanced
- Catalog kind
- skill
- Gateway key
a-share-multi-strategy- Source
- github.com/aifinlab/finclaw