SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsportfolio-risk-radar

portfolio-risk-radar

Data & analytics

View repository

Updated 10-15 19:55

About this skill

Portfolio Risk Radar

Available Tools

This skill can call the following MCP data services, selected 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:AnalyzePortfolioRisk, AnalyzeFundRisk, GetFundsCorrelation, GetAssetAllocation, fund-equity-position, fund-recovery-ability, 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 report sentiment, wealth management products, macroeconomic data
  • Optional tools of this skill:MarketFundFlowRank, IndustryValuation

Core Principles

Charts first, concise text. Quantitative data such as risk scores and correlation matrices must be presented through visual charts generated by RenderEchart , with text used only to interpret key warning points and provide hedging suggestions.

Input Requirements

Required Information

  • List of held funds: fund code + holding amount/weight

Optional Information

  • Client risk level (to assess whether risk exceeds the limit)
  • Specific risk dimensions of concern

Execution Process

Step 1: Parse Holdings

  • Extract fund codes and weights
  • If only amounts are available, calculate relative weights

Step 2: Risk Dimension Scan (parallelize as much as possible)

qieman data source:

  • AnalyzePortfolioRisk: portfolio risk indicators (risk score, R-squared, residual variance)
  • AnalyzeFundRisk: risk score for each fund
  • GetFundsCorrelation: correlation between funds
  • GetAssetAllocation: asset allocation analysis (including radar chart scoring)
  • fund-equity-position: equity position
  • fund-recovery-ability: drawdown recovery capability

gildata-aidata data source (valuation risk supplement, optional):

  • IndustryValuation: obtain the valuation percentile (PE/PB) of key industries in the holdings to determine whether they are in an overvalued range
  • MarketFundFlowRank: check the capital flows of industries related to the holdings to determine whether there is a risk of capital outflow

Step 3: Risk Diagnosis

  • Concentration risk: whether the proportion of a single fund/industry/style is too high
  • Correlation risk: whether the correlation coefficient between funds is too high (>0.8 warning)
  • Liquidity risk: whether there are large redemption restrictions
  • Style drift risk: whether the fund's actual style deviates from its stated style
  • Drawdown risk: the match between the portfolio's maximum drawdown level and the client's tolerance
  • Valuation risk(if gildata-aidata data is available): whether the valuations of key industries are at historical highs

Step 4: Generate Visual Charts (must be executed, cannot be skipped)

Mustsequentially call RenderEchart to generate the following charts:

Chart 1: Five-Dimension Risk Radar Chart (must be generated)

Generate a radar chart using rating scores across five risk dimensions (high=1/medium=3/low=5). ECharts option reference:

{
  "title": { "text": "组合风险雷达", "left": "center" },
  "radar": {
    "indicator": [
      { "name": "集中度", "max": 5 },
      { "name": "相关性", "max": 5 },
      { "name": "流动性", "max": 5 },
      { "name": "回撤控制", "max": 5 },
      { "name": "风格稳定", "max": 5 }
    ],
    "shape": "circle"
  },
  "series": [{
    "type": "radar",
    "data": [{
      "value": [2, 3, 4, 2, 5],
      "name": "风险评估",
      "areaStyle": { "opacity": 0.3 },
      "lineStyle": { "color": "#ee6666" }
    }]
  }]
}

Score meaning: 5=safe (low risk), 3=watch (medium risk), 1=warning (high risk). Replace with actual scores.

Chart 2: Bar chart comparing risk scores of each fund (must be generated)

Use AnalyzeFundRisk the risk scores of each fund returned to generate a bar chart. ECharts option reference:

{
  "title": { "text": "各基金风险评分", "left": "center" },
  "tooltip": { "trigger": "axis" },
  "grid": { "left": "25%", "right": "10%" },
  "xAxis": { "type": "value", "max": 100 },
  "yAxis": { "type": "category", "data": ["基金A", "基金B", "基金C"] },
  "visualMap": { "show": false, "min": 0, "max": 100, "inRange": { "color": ["#91cc75", "#fac858", "#ee6666"] } },
  "series": [{
    "type": "bar",
    "data": [35, 58, 82],
    "label": { "show": true, "position": "right", "formatter": "{c}分" },
    "itemStyle": { "borderRadius": [0, 4, 4, 0] }
  }]
}

The higher the risk score, the more dangerous; display it intuitively through a visualMap color gradient (green→yellow→red).

Chart 3: Correlation heatmap (must be generated if there are ≥3 funds)

Use GetFundsCorrelation the correlation coefficient matrix returned to generate a heatmap. ECharts option reference:

{
  "title": { "text": "基金相关性矩阵", "left": "center" },
  "tooltip": { "formatter": "{c}" },
  "xAxis": { "type": "category", "data": ["基金A", "基金B", "基金C"], "axisLabel": { "rotate": 30 } },
  "yAxis": { "type": "category", "data": ["基金A", "基金B", "基金C"] },
  "visualMap": { "min": -1, "max": 1, "orient": "horizontal", "left": "center", "bottom": 0, "inRange": { "color": ["#313695", "#74add1", "#ffffbf", "#f46d43", "#a50026"] } },
  "series": [{
    "type": "heatmap",
    "data": [[0,0,1],[0,1,0.85],[0,2,0.32],[1,0,0.85],[1,1,1],[1,2,0.45],[2,0,0.32],[2,1,0.45],[2,2,1]],
    "label": { "show": true, "formatter": "{c}" }
  }]
}

The data format is [x index, y index, correlation coefficient]. Correlation coefficients >0.8 are marked red as a warning.

Step 5: Output the risk report

Output template

Output according to the following structure,Embed charts in the corresponding sections, with text kept concise and focused on warnings and recommendations：

## 组合风险雷达

### 一、风险总览

{风险五维雷达图}

综合风险等级：**{高/中/低}**，{一句话总评}。

| 风险维度 | 等级 | 简评 |
|----------|------|------|
| 集中度 | {高/中/低} | {一句话} |
| 相关性 | {高/中/低} | {一句话} |
| 流动性 | {高/中/低} | {一句话} |
| 回撤控制 | {高/中/低} | {一句话} |
| 风格稳定 | {高/中/低} | {一句话} |

### 二、个基风险

{各基金风险评分对比柱状图}

{1-2句解读：哪只基金风险最高、是否拉高组合整体风险}

### 三、持仓相关性

{相关性热力图}

{1-2句解读：是否存在高度重叠、分散化程度}

### 四、风险预警与对冲建议

1. **{风险1}**：{一句话描述} → 建议：{具体操作}
2. **{风险2}**：{一句话描述} → 建议：{具体操作}
3. **{风险3}**：{一句话描述} → 建议：{具体操作}

---
*风险评估基于历史数据和量化模型，不构成投资建议。市场有风险，投资需谨慎。*

Notes

  • Charts are mandatory items: The risk radar chart and fund risk comparison bar chart are required items
  • Distinguish from comprehensive diagnosis: This Skill focuses on risk dimensions and does not evaluate returns
  • Do not create panic: State risks objectively and do not use sensational expressions
  • Actionability: Each risk point must be given specific hedging suggestions
  • Concise text: Keep the full text within 600-1000 words (excluding charts)