# China Clean Data Xls

Clean and normalize A-share financial data for modeling.

- Repository: https://github.com/jwangkun/claude-for-financial-services-cn (881 stars)
- Category: Engineering
- 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-clean-data-xls -g -a claude-code -y`
Codex: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-clean-data-xls -g -a codex -y`
Cursor: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-clean-data-xls -g -a cursor -y`
Gemini CLI: `npx skills add jwangkun/claude-for-financial-services-cn --skill china-clean-data-xls -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add jwangkun/claude-for-financial-services-cn`

## Description

Clean and normalize A-share financial data for modeling. Adapts the original clean-data-xls skill for Chinese financial statements, CAS conventions, and A-share data formats. Triggers on "A股数据清洗", "财务数据清洗", "clean financial data China", "数据清洗", or "normalize financial statements".

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

# china-clean-data-xls

## Purpose

Clean and normalize **A股财务数据**, prepare raw financial data from 巨潮 filings for modeling and analysis.

## 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_financials(ticker, "income")     → Raw income statement
get_financials(ticker, "balance")    → Raw balance sheet
get_financials(ticker, "cashflow")   → Raw cash flow statement
```

### Secondary Sources
- 巨潮, original filings (PDF/HTML)
- 审计报告, audited figures

## Workflow

### Step 1: Data Extraction

**Extract from source documents:**

| Document | Key Data | Format |
|----------|----------|--------|
| 资产负债表 | Assets, liabilities, equity | 千元 |
| 利润表 | Revenue, expenses, profit | 千元 |
| 现金流量表 | Operating, investing, financing CF | 千元 |
| 报表附注 | Detail breakdowns | Text/number |
| 审计报告 | Audit opinion, adjustments | Text |

**Extraction checklist:**
- [ ] All periods extracted (typically 3-5 years)
- [ ] Quarterly data if needed
- [ ] Prior year comparatives
- [ ] Notes and footnotes captured

### Step 2: Normalize Units

**Unit standardization:**

| Issue | Solution |
|-------|----------|
| 千元 vs 万元 vs 元 | Standardize to 万元 |
| Different report dates | Align to same period-end |
| Segment data | Map to consistent segments |
| Currency | All CNY |

**Unit conversion:**
```
From 千元: divide by 10 → 万元
From 元: divide by 10,000 → 万元
From 亿元: multiply by 10,000 → 万元
```

### Step 3: Handle CAS-Specific Items

**CAS vs IFRS mapping:**

The rest: https://github.com/jwangkun/claude-for-financial-services-cn/blob/HEAD/agent-plugins/china-model-builder/skills/china-clean-data-xls/SKILL.md