# China Variance Commentary

Write variance commentary for A-share fund performance and portfolio changes.

- Repository: https://github.com/jwangkun/claude-for-financial-services-cn (881 stars)
- Category: Writing
- License: Apache-2.0
- Last updated: 2026-09-14
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-variance-commentary -g -a claude-code -y`
Codex: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-variance-commentary -g -a codex -y`
Cursor: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-variance-commentary -g -a cursor -y`
Gemini CLI: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-variance-commentary -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add jwangkun/claude-for-financial-services-cn`

## Description

Write variance commentary for A-share fund performance and portfolio changes. Adapts the original variance-commentary skill for fund accounting and Chinese fund reporting conventions. Triggers on "基金业绩点评", "组合表现分析", "variance commentary fund", "基金表现分析", "业绩归因", or "commentary on [fund] performance".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# china-variance-commentary

## Purpose

Write professional **基金业绩点评**, structured variance commentary on fund performance and portfolio changes.

## Data Sources

### Tier 0, 万得 Wind（最全面付费数据）
- 覆盖：A股/港美股/基金/指数/债券/宏观/研报/分析（44个工具）
- MCP 服务：`wind-mcp`（需 `WIND_API_KEY` 密钥，以 `ak_` 开头）
- 优势：全市场覆盖面最广、数据最全面、包含研报和量化分析
- 密钥申请：https://aifinmarket.wind.com.cn/#/home

### Tier 1, 同花顺 iFind（付费精确数据）/ AkShare MCP（Tier-2 免费备选）

```python
get_fund_data(fund_code)              → Fund NAV, performance
get_quote(ticker)                     → Individual security performance
get_index_data("000001")              → Benchmark data
```

### Secondary Sources
- 基金公司, fund performance data
- 托管行, custody data
- Wind / Choice, performance analytics

## Workflow

### Step 1: Gather Performance Data

**Performance snapshot:**

| Metric | Period | Benchmark | Active Return |
|--------|--------|-----------|--------------|
| 净值增长率 | X.XX% | X.XX% | X.XX% |
| 年化收益率 | X.XX% | X.XX% | X.XX% |
| 波动率 | X.XX% | X.XX% | |
| 夏普比率 | X.XX | | |
| 最大回撤 | X.XX% | | |
| 卡尔马比率 | X.XX | | |

### Step 2: Attribution Analysis

**Performance attribution:**

| Factor | Contribution | Description |
|--------|-------------|-------------|
| 资产配置 (Allocation) | X.XX% | Sector/security weight decisions |
| 个股选择 (Selection) | X.XX% | Security picking within sectors |
| 交互效应 (Interaction) | X.XX% | Combined effect |

### Step 3: Sector Attribution

**Sector performance:**

| Sector | Weight | Return | Contribution | Benchmark Weight | Benchmark Return | Allocation Effect | Selection Effect |
|--------|--------|--------|-------------|-----------------|-----------------|-----------------|-----------------|
| | | | | | | | |
| **Total** | **100%** | | | | | | |

### Step 4: Top/Bottom Contributors

**Best/worst performers:**

The rest: https://github.com/jwangkun/claude-for-financial-services-cn/blob/HEAD/agent-plugins/china-pitch-agent/skills/china-variance-commentary/SKILL.md