SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsasset-allocation-optimizer

asset-allocation-optimizer

Design & creation

View repository

Updated 10-15 19:55

About this skill

Asset Allocation Optimization

Available Tools

This skill can call the following MCP data services, selecting them as needed during the execution process:

Yingmi Financial Data (qieman)

  • Service address:https://dashscope.aliyuncs.com/api/v1/mcps/Qieman/sse
  • Core capabilities: fund search/diagnosis, portfolio analysis/backtesting, asset allocation plans, CFP toolchain, chart rendering
  • Main tools of this skill:GetAssetAllocationPlan, GetCompositeModel, GetFundAssetClassAnalysis, MonteCarloSimulate, GetLatestQuotations, RenderEchart

Hundsun Juyuan Financial Data (gildata-aidata)

  • Service address: obtained after activating the Hundsun Juyuan MCP service, in the format https://dashscope.aliyuncs.com/api/v1/mcps/<your-mcp-id>/mcp
  • Core capabilities: individual stock research (A/H/US), financial statements, capital flows, research reports and public sentiment, wealth management products, macroeconomic data
  • Optional tools of this skill:MacroIndustryEDB, IndustryValuation

Core Principles

Charts first, concise text. Quantitative data such as asset allocation ratios, rebalancing gaps, and return simulations must be generated through RenderEchart into visual charts for presentation; text is only used to interpret allocation logic and implementation suggestions.

Input Requirements

Required Information

  • Client risk level: R1-R5
  • Investable amount or AUM

Optional Information

  • Overview of current holdings (used to analyze allocation gaps)
  • Investment horizon preference
  • Expected annualized return or maximum tolerable drawdown
  • Special requirements (such as "no equities" or "want to add gold")

If the user only says "help me make an allocation plan," ask follow-up questions about risk level and investable amount.

Execution Process

Step 1: Information Collection and Requirement Confirmation

  • Parse the client context and extract risk level, AUM, and current holdings
  • Determine allocation constraints

Step 2: Obtain the Baseline Allocation Plan

  • Call GetAssetAllocationPlan and pass in the three investment parameters (expected return / maximum drawdown / investment horizon, at least one)

Step 3: Implement into Specific Products

  • Call GetCompositeModel to obtain the composite model by plan ID

Step 4: Analyze Current Holdings Gaps (if holdings data is available)

  • Call GetFundAssetClassAnalysis to conduct look-through analysis of the asset class distribution of current holdings
  • Compare the target plan with the current allocation and calculate gaps for each major asset class

Step 5: Return and Risk Simulation

  • Call MonteCarloSimulate to run a Monte Carlo simulation on the allocation plan

Step 6: Market Environment Reference

  • Call GetLatestQuotations(qieman) to understand the current market environment
  • Optional: call MacroIndustryEDB(gildata-aidata) to obtain the latest macroeconomic indicators (GDP growth, CPI, interest rates, etc.) and provide macroeconomic context for allocation decisions
  • Optional: call IndustryValuation(gildata-aidata) to view valuation percentiles of major industries and assist in judging the timing of equity allocation

Step 7: Generate Visual Charts (must be executed, cannot be skipped)

Mustsequentially call RenderEchart to generate the following charts:

Chart 1: Target Asset Allocation Pie Chart (Must Be Generated)

Generate a pie chart using the weights of each major asset class in the target plan. ECharts option reference:

{
  "title": { "text": "目标资产配置", "left": "center" },
  "tooltip": { "trigger": "item", "formatter": "{b}: {d}%" },
  "legend": { "orient": "vertical", "left": "left", "top": "middle" },
  "color": ["#5470c6", "#91cc75", "#fac858", "#ee6666", "#73c0de"],
  "series": [{
    "type": "pie",
    "radius": ["40%", "70%"],
    "center": ["55%", "50%"],
    "itemStyle": { "borderRadius": 8 },
    "label": { "formatter": "{b}\n{d}%" },
    "data": [
      { "name": "权益类", "value": 30 },
      { "name": "固收类", "value": 40 },
      { "name": "固收+", "value": 15 },
      { "name": "现金管理", "value": 10 },
      { "name": "另类/商品", "value": 5 }
    ]
  }]
}

Replace with the actual plan weights.

Chart 2: Current vs Target Comparison Bar Chart (Must Be Generated If There Is a Current Portfolio)

Generate a grouped bar chart using the proportions of each major asset class in the current allocation and the target allocation to visually show the gaps. ECharts option reference:

{
  "title": { "text": "当前配置 vs 目标配置", "left": "center" },
  "tooltip": { "trigger": "axis" },
  "legend": { "top": "bottom" },
  "xAxis": { "type": "category", "data": ["权益类", "固收类", "固收+", "现金管理", "另类"] },
  "yAxis": { "type": "value", "axisLabel": { "formatter": "{value}%" } },
  "series": [
    { "name": "当前配置", "type": "bar", "data": [45, 20, 10, 20, 5], "itemStyle": { "borderRadius": [4,4,0,0] } },
    { "name": "目标配置", "type": "bar", "data": [30, 40, 15, 10, 5], "itemStyle": { "borderRadius": [4,4,0,0] } }
  ]
}

Replace with actual data.

Chart 3: Return Simulation Range Chart (Must Be Generated)

Generate a bar chart using the three-scenario return rate data from the Monte Carlo simulation. ECharts option reference:

{
  "title": { "text": "预期收益模拟（蒙特卡洛）", "left": "center" },
  "tooltip": { "trigger": "axis" },
  "legend": { "top": "bottom" },
  "xAxis": { "type": "category", "data": ["1年", "3年", "5年"] },
  "yAxis": { "type": "value", "axisLabel": { "formatter": "{value}%" } },
  "series": [
    { "name": "悲观(25%)", "type": "bar", "stack": "range", "data": [-3, 2, 8], "itemStyle": { "color": "#ee6666", "borderRadius": [0,0,0,0] } },
    { "name": "中性(50%)", "type": "bar", "stack": "range", "data": [5, 15, 28], "itemStyle": { "color": "#fac858" } },
    { "name": "乐观(75%)", "type": "bar", "stack": "range", "data": [12, 30, 52], "itemStyle": { "color": "#91cc75", "borderRadius": [4,4,0,0] } }
  ]
}

Replace with actual simulation data. Note: In a stacked bar chart, the data of each layer is cumulative, so differences need to be calculated. If it is not convenient to use a stacked chart, it can also be changed to a grouped bar chart.

Output Template

Output according to the following structure,embed charts in the corresponding sections, and keep the text concise：

## 资产配置优化方案

### 一、配置需求
| 项目 | 内容 |
|------|------|
| 风险等级 | {R等级} |
| 可投资金额 | {X}万 |
| 投资期限 | {X} |
| 配置目标 | {目标描述} |

### 二、推荐配置

{目标资产配置饼图}

| 资产大类 | 目标占比 | 建议金额 | 作用 |
|----------|---------|---------|------|
| 权益类 | {X}% | {X}万 | 收益增强 |
| 固收类 | {X}% | {X}万 | 底仓稳健 |
| ... | ... | ... | ... |

### 三、调仓建议（如有当前持仓）

{当前vs目标对比柱状图}

{2-3句解读：主要缺口在哪、需要增减配的方向}

### 四、收益模拟

{收益模拟区间图}

{2-3句通俗解读：持有X年大概率收益区间，亏损概率}

### 五、具体落地产品
| 资产类别 | 建议产品 | 配置金额 |
|----------|---------|---------|
| {类别} | {产品名}({代码}) | {X}万 |

### 六、实施建议
1. {分步实施建议}
2. {定期再平衡建议}

---
*配置方案基于量化模型和历史数据，收益模拟不代表实际收益。投资有风险，配置需谨慎。*

Notes

  • Charts are mandatory: The allocation pie chart and the return simulation chart are required items
  • Compliance requirements: The return simulation must clearly indicate its "simulated" nature and does not equal a return promise
  • Suitability matching: The risk level of the plan must not exceed the client's risk level
  • Liquidity guarantee: The proportion of cash management assets must not be less than 5-10%
  • Concise text: Keep the full text within 800-1200 words (excluding charts)