@v587d/capital-generation 2.7.3 → 2.7.5

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-clean-data-xls/SKILL.md

@@ -0,0 +1,237 @@
+---
+name: china-clean-data-xls
+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".
+---
+
+# 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:**
+
+| CAS Line Item | Equivalent | Notes |
+|---------------|-----------|-------|
+| 营业收入 | Revenue | Net of VAT |
+| 营业成本 | COGS | Includes VAT |
+| 税金及附加 | Tax & surcharges | 城建税, 教育费附加 |
+| 销售费用 | SG&A (selling) | |
+| 管理费用 | G&A | |
+| 研发费用 | R&D | Separated from G&A in new CAS |
+| 财务费用 | Interest & finance costs | |
+| 投资收益 | Investment income | Including 联营/合营 |
+| 公允价值变动 | Fair value change | |
+| 信用减值损失 | Credit impairment | New CAS 22 |
+| 资产减值损失 | Asset impairment | |
+| 资产处置收益 | Asset disposal | |
+| 营业外收入 | Non-operating income | Including 政府补助 |
+| 营业外支出 | Non-operating expense | |
+| 所得税费用 | Income tax | |
+| 净利润 | Net income | |
+| 归母净利润 | Net income to parent | Key metric |
+| 扣非净利润 | Non-GAAP net income | |
+
+### Step 4: Fix Common Data Issues
+
+**Common issues and fixes:**
+
+| Issue | Detection | Fix |
+|-------|-----------|-----|
+| Missing periods | Gap in data | Flag for manual fill |
+| Restated figures | Footnote "重述" | Use most recent restatement |
+| Segment reclassification | Note disclosure | Map to new segments |
+| One-time items | Large/unusual items | Flag for normalization |
+| Related party | 关联交易标注 | Identify and quantify |
+| Accounting change | Policy change note | Adjust comparables |
+| Error | Doesn't sum | Investigate and correct |
+
+### Step 5: Revenue Breakdown
+
+**Revenue by type:**
+
+| Type | CAS Line | Notes |
+|------|----------|-------|
+| 主营业务收入 | Core revenue | Main business |
+| 其他业务收入 | Other revenue | Ancillary |
+| 合计 | Total revenue | |
+
+**Revenue by geography (if disclosed):**
+
+| Region | Current Year | Prior Year | Growth |
+|--------|-------------|------------|--------|
+| 国内 | | | |
+| 海外 | | | |
+| 合计 | | | |
+
+### Step 6: Expense Normalization
+
+**Normalize non-recurring items:**
+
+| Item | Treatment |
+|------|-----------|
+| 资产处置收益/损失 | Exclude from operations |
+| 政府补助 (non-recurring) | Exclude or note separately |
+| 诉讼/罚款 | Exclude |
+| 减值 (one-time) | Exclude or normalize |
+| 并购相关费用 | Exclude |
+
+**Adjusted metrics:**
+```
+调整后营业收入 = 营业收入 - 其他业务收入
+调整后营业成本 = 营业成本 (core only)
+调整毛利率 = 调整后毛利 / 调整后收入
+```
+
+### Step 7: Balance Sheet Clean-up
+
+**Balance sheet mapping:**
+
+| CAS Item | Modeling Category |
+|----------|------------------|
+| 货币资金 | Cash & equivalents |
+| 交易性金融资产 | Short-term investments |
+| 应收票据 | Notes receivable |
+| 应收账款 | Accounts receivable |
+| 预付款项 | Prepayments |
+| 其他应收款 | Other receivables |
+| 存货 | Inventory |
+| 其他流动资产 | Other current assets |
+| 长期股权投资 | Long-term investments |
+| 固定资产 | PPE |
+| 在建工程 | Construction in progress |
+| 无形资产 | Intangibles |
+| 商誉 | Goodwill |
+| 长期待摊费用 | Deferred charges |
+| 其他非流动资产 | Other non-current |
+| 短期借款 | Short-term debt |
+| 应付票据 | Notes payable |
+| 应付账款 | Accounts payable |
+| 合同负债 | Contract liabilities |
+| 应付职工薪酬 | Accrued compensation |
+| 应交税费 | Taxes payable |
+| 其他应付款 | Other payables |
+| 一年内到期非流动负债 | Current portion LTD |
+| 长期借款 | Long-term debt |
+| 应付债券 | Bonds payable |
+| 预计负债 | Provisions |
+| 递延所得税负债 | DTL |
+| 其他非流动负债 | Other non-current |
+| 股本 | Share capital |
+| 资本公积 | Capital reserve |
+| 盈余公积 | Retained earnings (statutory) |
+| 未分配利润 | Retained earnings |
+| 归属于母公司股东权益 | Parent equity |
+| 少数股东权益 | Minority interest |
+
+### Step 8: Quality Checks
+
+**Data quality checklist:**
+
+| Check | Pass Criteria |
+|-------|--------------|
+| Balance sheet balances | Assets = Liabilities + Equity |
+| Cash flow ties | CF = ending cash - beginning cash |
+| Revenue matches | Cross-check with segment data |
+| Tax reasonable | Tax / pre-tax income ~25% |
+| Depreciation consistent | D&A / PPE stable |
+| Interest matches | Interest / debt reasonable |
+
+## China-Specific Data Issues
+
+### Common Issues
+
+| Issue | Example | Fix |
+|-------|---------|-----|
+| 单位不一致 | Some 千元, some 元 | Standardize |
+| 会计政策变更 | Revenue recognition change | Adjust comparables |
+| 报表格式变化 | New line items | Map to old format |
+| 追溯调整 | Prior period restatement | Use restated figures |
+| 外币报表 | Subsidiary in USD | Convert to CNY |
+
+### CAS-Specific Treatments
+
+| Item | CAS Treatment |
+|------|--------------|
+| 研发费用 | Must be expensed (not capitalized, generally) |
+| 政府补助 | 总额法 vs 净额法 |
+| 股份支付 | Expensed over vesting period |
+| 保险合同 | CAS 25 (if applicable) |
+
+## Quality Checks
+
+Before passing data for modeling:
+- [ ] All periods complete
+- [ ] Units standardized
+- [ ] Balance sheet balances
+- [ ] Cash flow ties
+- [ ] CAS items correctly mapped
+- [ ] Non-recurring items flagged
+- [ ] Restatements applied
+- [ ] Quality issues documented
+> **Data Source Mode Switch**: Set env var `IFIND_DATA_SOURCE_MODE` to control data source preference.
+> - `ifind-only` (strict): Use iFind only, error if unavailable
+> - `ifind-fallback` (default): iFind preferred, fallback to AkShare
+> - `akshare-only`: Skip iFind, use AkShare only
+> - `wind-only`: Wind only, error if unavailable
+> - `wind-fallback`: Wind first, fallback to iFind → AkShare

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-comps/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: china-comps
+description: Comparable company analysis for A-share stocks. Uses AkShare MCP to build peer groups, pull financial data, compute valuation multiples (PE, PB, PS), and assess relative value within a Chinese industry sector.
+---
+
+# china-comps
+
+## Data Sources (Multi-Tier)
+
+### 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）
+Use ifind MCP when a valid `IFIND_AUTH_TOKEN` is configured.
+
+```python
+ifind_get_stock_info(ticker)             → Company profile, multiples
+ifind_get_stock_financials(ticker, ...)  → Revenue, net income, margins
+ifind_search_stocks(query)               → Industry-wide stock screening
+```
+
+### Tier 2 — AkShare（免费开源数据）
+Fallback when iFind is unavailable.
+
+```python
+get_quote(ticker)              → Price, PE, PB, market cap
+get_financials(ticker, "income", "annual")  → Revenue, net income
+get_financials(ticker, "balance", "annual") → Book value
+get_stock_info(ticker)         → Business description
+```
+
+> **数据源模式开关**: 当环境变量 `IFIND_DATA_SOURCE_MODE=ifind-only` 时，仅使用 iFind 数据源，禁用 AkShare 降级。
+
+---
+name: china-comps
+description: Comparable company analysis for A-share stocks. Uses the AkShare MCP to build peer groups, pull financial data, compute valuation multiples (PE, PB, PS), and assess relative value within a Chinese industry sector. Use instead of the original comps-analysis skill when dealing with Chinese-listed equities.
+---
+
+# china-comps
+
+## Workflow
+
+### 1. Define the peer group
+
+Start with the target stock, then use `get_industry_stocks(industry="<行业名称>")` to get the full peer set for that industry. Common industry names used in the 东方财富 classification:
+
+| Industry | Example Leaders |
+|----------|-----------------|
+| 白酒 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 半导体 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 电池 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 银行 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 证券 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 保险 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 医疗器械 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 光伏设备 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 汽车整车 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+| 软件开发 | {{SECTOR_LEADER}}, {{CHALLENGER_1}}, {{CHALLENGER_2}} |
+
+### 2. Pull financial data for each peer
+
+```
+For each ticker in the peer set:
+  get_quote(ticker)         → price, PE, PB, market cap
+  get_financials(ticker, "income", "annual")     → revenue, net income
+  get_financials(ticker, "balance", "annual")    → book value, debt
+  get_stock_info(ticker)    → business description
+```
+
+### 3. Compute standard multiples
+
+| Multiple | Formula | AkShare source field |
+|----------|---------|---------------------|
+| PE (TTM) | Price / EPS TTM | `get_quote` → 动态市盈率 |
+| PB | Price / Book Value per share | `get_quote` → 市净率 |
+| PS (TTM) | Market Cap / Revenue TTM | Compute from market cap + revenue |
+| EV/EBITDA | Enterprise Value / EBITDA | Compute from market cap + debt - cash |
+| Dividend Yield | DPS / Price | `get_quote` → 股息率 |
+
+### 4. Present the comps table
+
+Sort by market cap (largest first). Flag outliers (>2 standard deviations from mean). Include:
+- Ticker, company name, price
+- Market cap (亿 CNY)
+- PE, PB, PS
+- Revenue growth %, Net margin %
+- 52-week high/low
+
+### 5. Relative value assessment
+
+- If target's PE is >1 std dev above peer mean → potentially overvalued
+- If target's PE is >1 std dev below peer mean → potentially undervalued
+- Flag companies with negative earnings separately
+- Compare PEG ratios (PE / growth rate) when growth data is available
+
+## Notes
+
+- All financial data from AkShare is based on Chinese accounting standards (CAS), not IFRS/US GAAP
+- Chinese market has 涨跌停 limits (±10% for main board, ±20% for ChiNext/STAR)
+- A-share market cap includes both circulating (流通) and non-circulating shares — check if the user wants 流通市值 or 总市值
+- For cross-market comps (A-share vs HK-listed), note that A-shares typically trade at a premium

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-comps-analysis/SKILL.md

@@ -0,0 +1,196 @@
+---
+name: china-comps-analysis
+description: Comparable company analysis for A-share equities. Adapts the original comps-analysis skill for Chinese market data sources, A-share trading multiples, and domestic peer selection. Triggers on "A股可比公司", "可比分析", "comps China", "peer comparison A-share", "可比公司分析", or "trading comps [industry]".
+---
+
+# china-comps-analysis
+
+> 本文件相对上游 `d7585ca` 快照做过合规改写（取数与凭据口径），逐条记在快照根目录的 UPSTREAM.md；方法论、阈值与输出模板未改。
+
+## Purpose
+
+Build **A股可比公司分析** — peer group multiples comparison adapted for the Chinese equity market.
+
+## Data Sources
+
+This section says **what to ask the host's retrieval path for**. It is not a set of calls made from here: this plugin obtains data through exactly one entry — the main agent delegating it — and a comps sheet carries no data-service key and issues no interface call.
+
+Hand over a brief naming the peer tickers, the fields, and one shared as-of date:
+
+- Trading multiples inputs per name: 最新价, PE / PB / PS, 市值, 股本
+- Financials per name: revenue and 归母净利润 for the LTM window, 资产负债表 for book value and 有息负债, plus the 折旧摊销 needed for EBITDA
+- Peer universe: the industry constituents for the 东方财富 category being used
+- Filings: the 定期报告 behind any figure that has to be checked against the disclosure rather than a screen
+
+In a host that splits roles, delegate that brief rather than searching from this step, then build the table from what comes back. A peer whose figures did not come back stays out of the median — it is not filled in with a remembered multiple.
+
+## Workflow
+
+### Step 1: Select Peer Group
+
+**Peer selection criteria:**
+
+| Criterion | China Context |
+|-----------|---------------|
+| Industry | Same 东方财富 industry category |
+| Market cap | ±3x of subject company |
+| Revenue | ±2x of subject company |
+| Growth | Similar revenue growth profile |
+| Profitability | Comparable margins |
+| Business model | Same/related business model |
+| Geography | China-focused (A-share only) |
+| Listing status | All A-share (include 北交所 if relevant) |
+
+**Typical peer count:** 8-15 companies
+
+### Step 2: Collect Financial Data
+
+**Data to collect for each peer:**
+
+| Data Item | Source | Notes |
+|-----------|--------|-------|
+| Current price | 宿主取数返回 | as-of 日期与其余行统一 |
+| Market cap | Calculated | Shares outstanding × price |
+| Revenue (LTM) | 宿主取数返回（利润表） | |
+| Net income (LTM) | 宿主取数返回（归母净利润） | |
+| EPS ( diluted ) | 宿主取数返回 | |
+| Book value | 资产负债表 | |
+| EBITDA | Calculate | Net income + tax + interest + D&A |
+| EV | Calculate | Market cap + net debt |
+
+The `Source` column is filled with what the retrieval actually returned — a dataset reference from the host's data path or the disclosure document behind it — never with a vendor name, and never left implied.
+
+### Step 3: Calculate Trading Multiples
+
+**Standard multiples:**
+
+| Multiple | Formula | Typical Range (A-share) |
+|----------|---------|------------------------|
+| P/E (动态) | Price / 预测EPS | 10-50x |
+| P/E (TTM) | Price / TTM EPS | 10-50x |
+| P/E (静态) | Price / 上年EPS | 10-50x |
+| PB | Price / 每股净资产 | 1-10x |
+| PS | EV / Revenue | 1-10x |
+| EV/EBITDA | EV / EBITDA | 5-20x |
+| PEG | P/E / Growth | 0.5-2.0 |
+| 股息率 | Dividend / Price | 0-5% |
+| ROE | Net income / Equity | 5-30% |
+
+**Multiples calculation notes:**
+- P/E: use 归母净利润 (net income attributable to parent)
+- PB: use 归属于母公司股东权益
+- EBITDA: approximate as 营业利润 + 折旧摊销 (if D&A not separately stated)
+
+### Step 4: Peer Comparison Table
+
+**Standard comps table:**
+
+| Company | Ticker | Market Cap (亿) | P/E (TTM) | P/B | P/S | EV/EBITDA | Revenue Growth | Net Margin | ROE |
+|---------|--------|----------------|-----------|-----|-----|-----------|---------------|------------|-----|
+| Subject | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+| Peer 1 | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+| Peer 2 | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+| Peer 3 | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+| ... | | | | | | | | | |
+| Median | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+| Mean | | | X.Xx | X.X | X.X | X.X | X% | X% | X% |
+
+### Step 5: Identify Outliers
+
+**Outlier analysis:**
+
+| Company | P/E | vs Median | Reason for Premium/Discount |
+|---------|-----|-----------|----------------------------|
+| | | ±X% | Growth, margin, quality, sentiment |
+
+**Common reasons for A-share premium/discount:**
+- 增速 (Growth rate)
+- 盈利能力 (Profitability / ROE)
+- 行业地位 (Market position)
+- 技术壁垒 (Technology moat)
+- 管理层质量 (Management quality)
+- 流动性 (Liquidity — 北向资金持仓)
+- 概念/题材 (Theme / concept premium)
+- 治理结构 (Corporate governance)
+
+### Step 6: Valuation Range
+
+**Derive valuation range:**
+
+| Method | Low | Mid | High | Rationale |
+|--------|-----|-----|------|-----------|
+| P/E | Xx | Xx | Xx | Based on peer range |
+| P/B | Xx | Xx | Xx | Based on peer range |
+| P/S | Xx | Xx | Xx | Based on peer range |
+| EV/EBITDA | Xx | Xx | Xx | Based on peer range |
+
+**Implied price range:**
+- Low: ¥XX (using low multiples + conservative assumptions)
+- Mid: ¥XX (using median multiples)
+- High: ¥XX (using high multiples + optimistic assumptions)
+
+### Step 7: Relative Valuation Conclusion
+
+**Valuation summary:**
+
+```
+可比公司估值结论
+
+当前股价: ¥XX
+目标价区间: ¥XX - ¥XX
+当前估值水平: [Premium/Discount] vs  peers
+
+关键结论:
+1. 相对估值: 较同业 [低/中/高]
+2. 主要驱动: [Growth / Margin / Quality]
+3. 估值折价/溢价原因: [Explanation]
+
+投资建议: [Buy / Hold / Sell]
+```
+
+## China-Specific Considerations
+
+### A-share Multiples Quirks
+
+| Issue | Impact | Mitigation |
+|-------|--------|-----------|
+| 盈利波动大 | TTM earnings volatile | Use 3Y average |
+| 一次性损益 | Distorts P/E | Use 扣非净利润 for P/E |
+| 亏损公司 | Negative P/E meaningless | Use P/S or EV/EBITDA |
+| 新股次新股 | Limited history | Use 静态市盈率 cautiously |
+| ST股票 | Distressed | Exclude from peer set |
+
+### Chinese Market Premiums
+
+| Factor | Typical Premium |
+|--------|----------------|
+| 消费龙头 (Consumer leader) | +20-50% |
+| 科技/创新 (Tech/innovation) | +30-100% |
+| 医药 (Pharma) | +15-40% |
+| 国企 (SOE) | -10 to -30% |
+| 高股息 (High dividend) | -5 to +10% |
+| 北向资金重仓 | +5-20% |
+
+### 东方财富 Industry Categories
+
+**Common categories for peer selection:**
+- 白酒, 啤酒 — Beverages
+- 半导体, 芯片 — Semiconductors
+- 银行, 证券, 保险 — Financial services
+- 创新药, 医疗器械 — Healthcare
+- 光伏设备, 锂电池 — New energy
+- 汽车整车, 汽车零部件 — Auto
+- 软件开发, IT服务 — Software/IT
+- 房地产, 建材 — Real estate / Materials
+
+## Quality Checks
+
+Before delivering:
+- [ ] Peer group appropriate (similar size, growth, business model)
+- [ ] Every figure came back through the host's retrieval path, or is written up as missing
+- [ ] Multiples calculated correctly
+- [ ] Outliers explained
+- [ ] Valuation conclusion supported
+- [ ] Current price verified
+> 取数档位（接哪家数据服务、用哪个密钥）由宿主的凭据域决定：这张可比表不配置它，也不向使用者索取凭据。
+> 目标价区间与最后一行投资建议是把上面这些倍数写成一个结论的**推演练习**，本插件不据它下单，也不给仓位。

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-dcf/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: china-dcf
+description: DCF valuation model for A-share stocks on Chinese financial statements, with WACC built from China government bond yields and A-share specific ERP. Use instead of the original dcf-model skill for Chinese equities.
+---
+
+# china-dcf
+
+> 本文件相对上游 `d7585ca` 快照做过合规改写（取数与凭据口径），逐条记在快照根目录的 UPSTREAM.md；方法论、阈值与输出模板未改。
+
+## Data Sources
+
+A DCF is only as honest as the numbers handed to it, and this plugin has exactly one way to obtain numbers: the main agent delegates retrieval to the role that owns it. Nothing here calls a data interface, holds a key, or runs code.
+
+Write one brief that names the ticker, the fields, and the as-of date, and ask for:
+
+- 三表（年度，5 年窗口）：利润表、资产负债表、现金流量表 — the base for FCF history and for 折旧摊销 / CapEx
+- 行情与股本：最新价、市值、PE / PB、股本结构（beta 需要它和基准指数的收益序列）
+- 基准指数收益：上证指数的历史收益，用于 β 回归
+- 无风险与债务成本输入：中国 10Y 国债收益率（Rf）与 5 年期信用债收益（Kd 的起点）
+- 风险指标：宿主数据侧给出的 β / 波动率；拿不到就用同业 β 并写明用的是哪家同业
+
+In a host that splits roles, delegate that brief rather than reaching for a feed from here. Then build the model from what comes back; a field that did not come back stays a named gap, and the valuation runs as a sensitivity over it rather than on an invented level.
+
+
+
+
+## Key differences from US-market DCF
+
+| Parameter | US DCF Convention | China DCF Convention |
+|-----------|-------------------|---------------------|
+| Risk-free rate | US 10Y Treasury | China 10Y CGB (国债收益率, ~2.5-3.5%) |
+| Equity risk premium | ~5-6% (historical US) | ~6-8% (China A-share ERP) |
+| Tax rate | US corporate 21% | China corporate 25% (高新技术企业 15%) |
+| Terminal growth | US GDP growth (~2%) | China GDP growth (~4-5%) |
+| Currency | USD | CNY |
+| Reporting standard | US GAAP / IFRS | CAS (中国会计准则) |
+
+## Workflow
+
+### Step 1: Pull financials
+
+Retrieve, through the host's data path: 利润表 / 资产负债表 / 现金流量表 on an annual basis for the last 5 years. Ask for them as one brief with the ticker, the three statements, and the window, then take the returned dataset reference as the model's input record.
+
+### Step 2: Get market data
+
+Retrieve 最新价、市值、PE / PB for the subject, and the 上证指数 return history needed for β. Both asks go to the host's retrieval path with the same as-of date; β is then estimated from what came back, and if the benchmark history did not come back, say so and use a comparable-firm β labelled as such.
+
+### Step 3: Build projections
+
+- Project revenue using historical growth rates adjusted for China macro outlook
+- Assume 65-75% operating margin for 白酒 / high-margin sectors
+- Assume 15-25% operating margin for manufacturing
+- CapEx as % of revenue: check historical from cashflow statement
+
+### Step 4: Compute WACC
+
+```
+WACC = E/(D+E) * Ke + D/(D+E) * Kd * (1 - tax_rate)
+
+Ke = Rf + β * ERP
+  Rf   = China 10Y CGB yield（国债收益率）— ask the host's retrieval path for the current level; if it does not come
+         back, run the model as a sensitivity over a stated Rf band instead of assuming a number
+  β    = regression on 上证指数 returns (or use comparable firm beta)
+  ERP  = 6-8% (China-specific equity risk premium)
+
+Kd   = China 5Y corporate bond yield + credit spread
+```
+
+### Step 5: Terminal value
+
+```
+Terminal Value = FCF_(n+1) / (WACC - g)
+g = 3-4% for mature Chinese companies (China nominal GDP growth)
+```
+
+## Notes
+
+- Chinese fiscal year ends December 31 for most companies
+- 北向资金 (Northbound flow) data can be used as sentiment indicator
+- 商誉 (goodwill) impairments are common in China M&A — flag if goodwill > 30% of equity
+- Some Chinese financial statements are reported in 千元 (thousands of CNY) vs 元 — check the unit

package/selected-skills/claude-for-financial-services-cn/vertical-plugins/china-finance/skills/china-dcf-model/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: china-dcf-model
+description: Discounted cash flow (DCF) valuation model for A-share equities. This alias skill redirects to china-dcf, which provides comprehensive DCF modeling adapted for Chinese market conventions. Triggers on "A股DCF模型", "DCF估值", "DCF model China", "现金流折现", "discounted cash flow A-share", or "DCF [company]".
+---
+
+# china-dcf-model
+
+> **Note:** This skill is an alias/wrapper for `china-dcf`. For full DCF modeling guidance, see `china-dcf/SKILL.md`.
+
+## Purpose
+
+Provide access to **A股DCF估值** — discounted cash flow valuation adapted for Chinese market parameters.
+
+## Quick Reference
+
+### Core DCF Parameters (China)
+
+| Parameter | Typical Value | Source |
+|-----------|--------------|--------|
+| Risk-free rate | 2.0-3.0% | China 10Y CGB yield |
+| Equity risk premium | 6-8% | China-specific |
+| Beta | 0.8-1.2 | A-share historical |
+| Cost of debt | 3-6% | China corporate bond yields |
+| Terminal growth | 3-4% | China GDP long-term |
+| Tax rate | 25% (15% for 高新) | CAS |
+
+### Key Differences from US DCF
+
+| Aspect | US | China (A-share) |
+|--------|-----|-----------------|
+| Risk-free rate | UST 10Y | China 10Y CGB |
+| ERP | 5-6% | 6-8% (higher for EM) |
+| Terminal growth | 2-3% | 3-4% |
+| Tax rate | 21% (federal) | 25% (15% for 高新) |
+| Currency | USD | CNY |
+| Revenue units | $M | 万元 / 亿元 |
+
+### Quick Workflow
+
+1. **Project FCF** — 5-year explicit period
+2. **Calculate WACC** — Use China parameters
+3. **Discount FCF** — PV of explicit period
+4. **Terminal value** — Gordon growth or exit multiple
+5. **Enterprise value** — Sum of PVs
+6. **Equity value** — EV - Net debt + Minority interest
+7. **Value per share** — Equity value / Shares
+
+### Common Pitfalls
+
+| Pitfall | China-Specific Fix |
+|---------|-------------------|
+| Using US risk-free rate | Use China 10Y CGB |
+| Wrong tax rate | Verify 高新 enterprise status |
+| Revenue in USD | Convert to CNY |
+| Ignoring 增值税 | Revenue should be net of VAT |
+| Western terminal growth | Use 3-4% for China |
+
+### For Full Details
+
+See: `china-dcf/SKILL.md`
+
+## Quality Checks
+
+- [ ] All parameters China-appropriate
+- [ ] FCF projections reasonable
+- [ ] WACC components sourced
+- [ ] Terminal growth < GDP growth
+- [ ] Sensitivity analysis included