@baimingtao/lbs-agent 1.0.0

package/extensions/skills/optional/finance/dcf-model/SKILL.md

@@ -0,0 +1,850 @@
+---
+name: dcf-model
+description: 在 Excel 中构建机构级 DCF 估值模型 — 营收预测、FCF 构建、WACC、终值、Bear/Base/Bull 场景、5x5 敏感性分析表。与 excel-author 配套使用。用于内在价值权益分析。
+version: 1.0.0
+author: Anthropic (adapted by Nous Research)
+license: Apache-2.0
+platforms: [linux, macos, windows]
+metadata:
+  hermes:
+    tags: [finance, valuation, dcf, excel, openpyxl, modeling, investment-banking]
+    related_skills: [excel-author, pptx-author, comps-analysis, lbo-model, 3-statement-model]
+---
+
+## 环境
+
+这个 skill 假设使用 **headless openpyxl** — 你将在磁盘上生成一个 .xlsx 文件。
+对于单元格颜色、公式、命名区域和敏感性分析表，请遵循 `excel-author` skill 的规范。
+交付前请重新计算：`python /path/to/excel-author/scripts/recalc.py ./out/model.xlsx`。
+
+# DCF Model Builder
+
+## 概览
+
+这个 skill 遵循投行标准，为股票估值创建机构级的 DCF 模型。每次分析都会生成一个详细的 Excel 模型（在 DCF 表的底部包含敏感性分析）。
+
+## 工具
+
+- 默认使用用户提供的所有信息以及可用于获取数据的 MCP servers。
+
+## Critical Constraints - Read These First
+
+这些限制适用于整个 DCF 模型构建过程。开始前请仔细阅读：
+
+**Formulas Over Hardcodes (NON-NEGOTIABLE):**
+- 每个 forecast、margin、discount factor、PV 和 sensitivity 单元格必须是动态的 Excel 公式 — 绝对不能是 Python 计算后硬编码写入的数字
+- 使用 openpyxl 时：`ws["D20"] = "=D19*(1+$B$8)"` 是正确的；`ws["D20"] = calculated_revenue` 是错误的
+- 唯一允许硬编码的数字是：(1) 原始历史输入，(2) 假设 drivers（增长率、WACC 输入、terminal g），(3) 当前市场数据（股价、债务余额）
+- 如果你发现自己在 Python 中计算并写入结果 — 停止。当用户更改假设时，模型必须能够灵活调整。
+
+**Verify Step-by-Step With the User (DO NOT build end-to-end):**
+- 数据检索后 → 向用户展示原始输入块（revenue、margins、shares、net debt），并在进行预测前确认
+- 营收预测后 → 展示预测的 top line 和增长率，在构建 margin build 前确认
+- FCF 构建后 → 展示完整的 FCF 时间表，在计算 WACC 前确认逻辑
+- WACC 后 → 展示计算和输入，在折现前确认
+- Terminal value + PV 后 → 展示 equity bridge（EV → equity value → per share），在生成敏感性表前确认
+- 在每个阶段捕捉错误 — 如果在敏感性表构建完成后才发现 margin 假设错误，意味着下游的所有内容都要重建
+
+**Sensitivity Tables:**
+- **使用奇数行和列**（标准：5×5，有时 7×7）— 这保证了真正的中心单元格
+- **Center cell = base case.** 构建轴值，使得中间行表头和中间列表头完全等于模型的实际假设（例如，如果 base WACC = 9.0%，中间行就是 9.0%；如果 terminal g = 3.0%，中间列就是 3.0%）。中心单元格的输出因此必须等于模型的实际 implied share price — 这是对表格构建是否正确的 sanity check。
+- **突出显示中心单元格**，使用中蓝色填充（`#BDD7EE`）+ 粗体字体，以便立即可见哪个单元格是 base case。
+- 用完整的 DCF 重新计算公式填充所有单元格（通常是 3 个表 × 25 个单元格 = 75）
+- 使用 openpyxl 循环以编程方式编写公式
+- 没有占位符文本，没有线性近似，不需要手动步骤
+- 每个单元格必须针对该假设组合重新计算完整的 DCF
+
+**Cell Comments:**
+- 在创建每个硬编码值时添加单元格注释
+- 格式："Source: [System/Document], [Date], [Reference], [URL if applicable]"
+- 每个蓝色输入在移动到下一部分之前必须有一个注释
+- 不要推迟到最后或写 "TODO: add source"
+
+**Model Layout Planning:**
+- 在编写任何公式之前定义所有部分的行位置
+- 首先编写所有的 headers 和 labels
+- 其次编写所有的 section dividers 和空白行
+- 然后使用锁定的行位置编写公式
+- 创建后立即测试公式
+
+**Formula Recalculation:**
+- 交付前运行 `python recalc.py model.xlsx 30`
+- 修复所有错误，直到状态为 "success"
+- 要求零公式错误（#REF!, #DIV/0!, #VALUE! 等）
+
+**Scenario Blocks:**
+- 为 Bear/Base/Bull 情况创建单独的块
+- 在每个块内水平显示横跨预测年份的假设
+- 使用 IF 公式：`=IF($B$6=1,[Bear cell],IF($B$6=2,[Base cell],[Bull cell]))`
+- 验证公式引用正确的场景块单元格
+
+## DCF Process 工作流
+
+### Step 1: Data Retrieval and 验证
+
+从 MCP servers、用户提供的数据和网络获取数据。
+
+**Data Sources Priority:**
+1. **MCP Servers** (if configured) - 来自 Daloopa 等提供商的结构化财务数据
+2. **User-Provided Data** - 来自其研究的历史财务数据
+3. **Web Search/Fetch** - 需要时的当前价格、beta、债务和现金
+
+**Validation Checklist:**
+- 验证 net debt 与 net cash（对估值至关重要）
+- 确认稀释在外的流通股（检查近期的 buybacks/issuances）
+- 验证历史 margins 与商业模式一致
+- 将营收增长率与行业基准进行 cross-check
+- 验证税率合理（通常为 21-28%）
+
+### Step 2: Historical Analysis (3-5 years)
+
+分析并记录：
+- **Revenue growth trends**: 计算 CAGR，识别 drivers
+- **Margin progression**: 追踪 gross margin、EBIT margin、FCF margin
+- **Capital intensity**: D&A 和 CapEx 占营收的百分比
+- **Working capital efficiency**: NWC 变化占营收增长的百分比
+- **Return metrics**: ROIC、ROE 趋势
+
+创建汇总表显示：
+```
+Historical Metrics (LTM):
+Revenue: $X million
+Revenue growth: X% CAGR
+Gross margin: X%
+EBIT margin: X%
+D&A % of revenue: X%
+CapEx % of revenue: X%
+FCF margin: X%
+```
+
+### Step 3: Build Revenue Projections
+
+**Methodology:**
+1. 从最近的实际营收开始（LTM 或最近的财年）
+2. 应用于每个预测年份的增长率
+3. 同时显示美元金额和计算出的增长 %
+
+**Growth Rate Framework:**
+- Year 1-2: 反映短期可见性的较高增长
+- Year 3-4: 逐渐放缓至行业平均水平
+- Year 5+: 接近 terminal growth rate
+
+**Formula structure:**
+- Revenue(Year N) = Revenue(Year N-1) × (1 + Growth Rate)
+- Growth %(Year N) = Revenue(Year N) / Revenue(Year N-1) - 1
+
+**Three-scenario approach:**
+```
+Bear Case: Conservative growth (e.g., 8-12%)
+Base Case: Most likely scenario (e.g., 12-16%)
+Bull Case: Optimistic growth (e.g., 16-20%)
+```
+
+### Step 4: Operating Expense Modeling
+
+**Fixed/Variable Cost Analysis:**
+
+Operating expenses 应模拟现实的 operating leverage：
+- **Sales & Marketing**: 通常占营收的 15-40%，取决于商业模式
+- **Research & 开发**: 科技公司通常占 10-30%
+- **General & Administrative**: 通常占营收的 8-15%，随着公司规模扩大显示 leverage
+
+**Key principles:**
+- 所有百分比基于 REVENUE，而不是 gross profit
+- 模拟 operating leverage：百分比应随营收规模扩大而下降
+- 为 S&M, R&D, G&A 维持单独的明细项目
+- 计算 EBIT = Gross Profit - Total OpEx
+
+**Margin expansion framework:**
+```
+Current State → Target State (Year 5)
+Gross Margin: X% → Y% (justify based on scale, efficiency)
+EBIT Margin: X% → Y% (result of revenue growth + opex leverage)
+```
+
+### Step 5: Free Cash Flow Calculation
+
+**按正确的顺序构建 FCF：**
+
+```
+EBIT
+(-) Taxes (EBIT × Tax Rate)
+= NOPAT (Net Operating Profit After Tax)
+(+) D&A (non-cash expense, % of revenue)
+(-) CapEx (% of revenue, typically 4-8%)
+(-) Δ NWC (change in working capital)
+= Unlevered Free Cash Flow
+```
+
+**Working Capital Modeling:**
+- 计算为营收变化（delta revenue）的百分比
+- 典型范围：占营收变化的 -2% 到 +2%
+- 负数 = 现金来源（营运资金释放）
+- 正数 = 现金使用（营运资金积累）
+
+**Maintenance vs Growth CapEx:**
+- Maintenance CapEx: 维持当前运营（约占营收 2-3%）
+- Growth CapEx: 支持扩张（额外占营收 2-5%）
+- Total CapEx 应与公司的增长战略保持一致
+
+### Step 6: Cost of Capital (WACC) Research
+
+**CAPM Methodology for Cost of Equity:**
+
+```
+Cost of Equity = Risk-Free Rate + Beta × Equity Risk Premium
+
+Where:
+- Risk-Free Rate = Current 10-Year Treasury Yield
+- Beta = 5-year monthly stock beta vs market index
+- Equity Risk Premium = 5.0-6.0% (market standard)
+```
+
+**Cost of Debt Calculation:**
+
+```
+After-Tax Cost of Debt = Pre-Tax Cost of Debt × (1 - Tax Rate)
+
+Determine Pre-Tax Cost of Debt from:
+- Credit rating (if available)
+- Current yield on company bonds
+- Interest expense / Total Debt from financials
+```
+
+**Capital Structure Weights:**
+
+```
+Market Value Equity = Current Stock Price × Shares Outstanding
+Net Debt = Total Debt - Cash & Equivalents
+Enterprise Value = Market Cap + Net Debt
+
+Equity Weight = Market Cap / Enterprise Value
+Debt Weight = Net Debt / Enterprise Value
+
+WACC = (Cost of Equity × Equity Weight) + (After-Tax Cost of Debt × Debt Weight)
+```
+
+**Special Cases:**
+- **Net Cash Position**: If Cash > Debt, Net Debt is NEGATIVE
+  - Debt Weight may be negative
+  - WACC calculation adjusts accordingly
+- **No Debt**: WACC = Cost of Equity
+
+**Typical WACC Ranges:**
+- Large Cap, Stable: 7-9%
+- Growth Companies: 9-12%
+- High Growth/Risk: 12-15%
+
+### Step 7: Discount Rate Application (5-10 Year Forecast)
+
+**Mid-Year Convention:**
+- 假设现金流发生在年中
+- Discount Period: 0.5, 1.5, 2.5, 3.5, 4.5 等
+- Discount Factor = 1 / (1 + WACC)^Period
+
+**Present Value Calculation:**
+```
+For each projection year:
+PV of FCF = Unlevered FCF × Discount Factor
+
+Example (Year 1):
+FCF = $1,000
+WACC = 10%
+Period = 0.5
+Discount Factor = 1 / (1.10)^0.5 = 0.9535
+PV = $1,000 × 0.9535 = $954
+```
+
+**Projection Period Selection:**
+- **5 years**: 大多数分析的标准
+- **7-10 years**: 有较长跑道的高增长公司
+- **3 years**: 成熟、稳定的企业
+
+### Step 8: Terminal Value Calculation
+
+**Perpetuity Growth Method (Preferred):**
+
+```
+Terminal FCF = Final Year FCF × (1 + Terminal Growth Rate)
+Terminal Value = Terminal FCF / (WACC - Terminal Growth Rate)
+
+Critical Constraint: Terminal Growth < WACC (otherwise infinite value)
+```
+
+**Terminal Growth Rate Selection:**
+- Conservative: 2.0-2.5% (GDP growth rate)
+- Moderate: 2.5-3.5%
+- Aggressive: 3.5-5.0% (only for market leaders)
+
+**Do not exceed**: Risk-free rate or long-term GDP growth
+
+**Exit Multiple Method (Alternative):**
+```
+Terminal Value = Final Year EBITDA × Exit Multiple
+
+Where Exit Multiple comes from:
+- Industry comparable trading multiples
+- Precedent transaction multiples
+- Typical range: 8-15x EBITDA
+```
+
+**Present Value of Terminal Value:**
+```
+PV of Terminal Value = Terminal Value / (1 + WACC)^Final Period
+
+Where Final Period accounts for timing:
+5-year model with mid-year convention: Period = 4.5
+```
+
+**Terminal Value Sanity Check:**
+- 应占 Enterprise Value 的 50-70%
+- 如果 >75%，模型可能过度依赖终值假设
+- 如果 <40%，检查终值假设是否过于保守
+
+### Step 9: Enterprise to Equity Value Bridge
+
+**Valuation Summary Structure:**
+
+```
+(+) Sum of PV of Projected FCFs = $X million
+(+) PV of Terminal Value = $Y million
+= Enterprise Value = $Z million
+
+(-) Net Debt [or + Net Cash if negative] = $A million
+= Equity Value = $B million
+
+÷ Diluted Shares Outstanding = C million shares
+= Implied Price per Share = $XX.XX
+
+Current Stock Price = $YY.YY
+Implied Return = (Implied Price / Current Price) - 1 = XX%
+```
+
+**Critical Adjustments:**
+- **Net Debt = Total Debt - Cash & Equivalents**
+  - 如果为正：从 EV 中扣除（降低 equity value）
+  - 如果为负（Net Cash）：加到 EV 中（增加 equity value）
+- **Use Diluted Shares**: 包括 options、RSUs、convertible securities
+- **Other adjustments** (if applicable):
+  - Minority interests
+  - Pension liabilities
+  - Operating lease obligations
+
+**Valuation Output Format:**
+```csv
+Valuation Component,Amount ($M)
+PV Explicit FCFs,X.X
+PV Terminal Value,Y.Y
+Enterprise Value,Z.Z
+(-) Net Debt,A.A
+Equity Value,B.B
+,,
+Shares Outstanding (M),C.C
+Implied Price per Share,$XX.XX
+Current Share Price,$YY.YY
+Implied Upside/(Downside),+XX%
+```
+
+### Step 10: Sensitivity Analysis
+
+在 DCF 表的底部构建 **三个敏感性分析表**，显示估值如何随不同假设变化：
+
+1. **WACC vs Terminal Growth** - 显示 enterprise value 对折现率和永续增长率的敏感性
+2. **Revenue Growth vs EBIT Margin** - 显示 top-line 增长和 operating leverage 的影响
+3. **Beta vs Risk-Free Rate** - 显示对 cost of equity 组成部分的敏感性
+
+**Implementation**: 这些是简单的 2D 网格（不是 Excel 的 "Data Table" 功能），在每个单元格中都有公式。每个单元格必须包含针对该特定假设组合的完整 DCF 重新计算。关于使用 openpyxl 以编程方式填充所有 75 个单元格的详细要求，请参阅 Critical Constraints 部分。
+
+<correct_patterns>
+
+本节包含了构建 DCF 模型时应遵循的所有正确模式。
+
+### Scenario Block Selection 模式 - Follow This Approach
+
+**每个场景的假设组织在单独的块中：**
+
+**CRITICAL STRUCTURE - Three rows per section header:**
+
+```csv
+BEAR CASE ASSUMPTIONS (section header, merge cells across)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),12%,10%,9%,8%,7%
+EBIT Margin (%),45%,44%,43%,42%,41%
+
+BASE CASE ASSUMPTIONS (section header, merge cells across)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),16%,14%,12%,10%,9%
+EBIT Margin (%),48%,49%,50%,51%,52%
+
+BULL CASE ASSUMPTIONS (section header, merge cells across)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),20%,18%,15%,13%,11%
+EBIT Margin (%),50%,51%,52%,53%,54%
+```
+
+**Each scenario block MUST have a column header row** 在章节标题正下方显示预测年份（FY2025E、FY2026E 等）。没有这个，用户无法分辨哪个假设值对应哪一年。
+
+**How to reference assumptions - Create a consolidation column:**
+1. Case selector 单元格（例如 B6）包含 1=Bear, 2=Base, 或 3=Bull
+2. 创建一个带有 INDEX 或 OFFSET 公式的 consolidation column，从正确的场景块中提取数据
+3. 预测公式引用 consolidation column（干净的单元格引用）
+4. 每个场景块包含跨预测年份的完整 DCF 假设集
+
+**推荐 consolidation column pattern (using INDEX):**
+`=INDEX(B10:D10, 1, $B$6)`
+
+**NOT this - scattered IF statements throughout:**
+`=IF($B$6=1,[Bear block cell],IF($B$6=2,[Base block cell],[Bull block cell]))`
+
+consolidation column 方法集中了逻辑，使模型更容易 audit。
+
+### Correct Revenue Projection 模式
+
+**创建一个带有 INDEX 公式的 consolidation column，然后在预测中引用它：**
+
+**Step 1 - Consolidation column for FY1 growth:**
+`=INDEX([Bear FY1 growth]:[Bull FY1 growth], 1, $B$6)`
+
+**Step 2 - Revenue projection references the consolidation column:**
+`Revenue Year 1: =D29*(1+$E$10)`
+
+Where:
+- D29 = Prior year revenue
+- $E$10 = Consolidation column cell for FY1 growth (contains INDEX formula)
+- $B$6 = Case selector (1=Bear, 2=Base, 3=Bull)
+
+**This approach is cleaner than embedding IF statements in every projection formula** 并使得 audit 正在使用哪些场景假设变得容易得多。
+
+### Correct FCF Formula 模式
+
+**使用带有 INDEX 公式的 consolidation column，然后在 FCF 计算中引用它们：**
+
+**Consolidation column approach:**
+```csv
+Item,Formula,Reference
+D&A,=E29*$E$21,$E$21 = consolidation column for D&A %
+CapEx,=E29*$E$22,$E$22 = consolidation column for CapEx %
+Δ NWC,=(E29-D29)*$E$23,$E$23 = consolidation column for NWC %
+Unlevered FCF,=E57+E58-E60-E62,E57=NOPAT E58=D&A E60=CapEx E62=Δ NWC
+```
+
+**Each consolidation column cell contains an INDEX formula** 根据 case selector 从适当的场景块中提取数据。这使得预测公式保持干净且易于 audit。
+
+在编写公式之前，确认场景块行位置并设置 consolidation column。
+
+### Correct Cell Comment Format
+
+**Every hardcoded value needs this format:**
+
+"Source: [System/Document], [Date], [Reference], [URL if applicable]"
+
+**示例:**
+```csv
+Item,Source Comment
+Stock price,Source: Market data script 2025-10-12 Close price
+Shares outstanding,Source: 10-K FY2024 Page 45 Note 12
+Historical revenue,Source: 10-K FY2024 Page 32 Consolidated Statements
+Beta,Source: Market data script 2025-10-12 5-year monthly beta
+Consensus estimates,Source: Management guidance Q3 2024 earnings call
+```
+
+### Correct Assumption Table Structure
+
+**CRITICAL: Each scenario block requires THREE structural elements:**
+
+1. **Section header row** (merged cells): e.g., "BEAR CASE ASSUMPTIONS"
+2. **Column header row** showing years - THIS IS REQUIRED, DO NOT SKIP
+3. **Data rows** with assumption values
+
+**Structure:**
+```csv
+BEAR CASE ASSUMPTIONS (section header - merge across columns A:G)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),X%,X%,X%,X%,X%
+EBIT Margin (%),X%,X%,X%,X%,X%
+Terminal Growth,X%,,,,
+WACC,X%,,,,
+
+BASE CASE ASSUMPTIONS (section header - merge across columns A:G)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),X%,X%,X%,X%,X%
+EBIT Margin (%),X%,X%,X%,X%,X%
+Terminal Growth,X%,,,,
+WACC,X%,,,,
+
+BULL CASE ASSUMPTIONS (section header - merge across columns A:G)
+Assumption,FY1,FY2,FY3,FY4,FY5
+Revenue Growth (%),X%,X%,X%,X%,X%
+EBIT Margin (%),X%,X%,X%,X%,X%
+Terminal Growth,X%,,,,
+WACC,X%,,,,
+```
+
+**WITHOUT the column header row showing projection years (FY2025E, FY2026E, etc.), users cannot tell which assumption value corresponds to which year. This row is MANDATORY.**
+
+**Then create a consolidation column** （通常是右侧的下一列），根据 case selector 使用 INDEX 公式从选定的场景块中提取数据。你的预测公式引用的就是这个 consolidation column。
+
+### Correct Row Planning Process
+
+**1. Write ALL headers and labels FIRST:**
+```csv
+Row,Content
+1,[Company Name] DCF Model
+2,Ticker | Date | Year End
+4,Case Selector
+7,KEY ASSUMPTIONS
+26,Assumption headers
+27-31,Growth assumptions
+...,...
+```
+
+**2. Write ALL section dividers and blank rows**
+
+**3. THEN write formulas using the locked row positions**
+
+**4. Test formulas immediately after creation**
+
+**Think of it like construction:**
+- Good: Pour foundation, then build walls (stable structure)
+- Bad: Build walls, then pour foundation (walls collapse)
+
+**Excel version:**
+- Good: Add headers, then write formulas (formulas stable)
+- Bad: Write formulas, then add headers (formulas break)
+
+### Correct Sensitivity Table Implementation
+
+**IMPORTANT**: 这些不是 Excel 的 "Data Table" 功能。这些是你使用 openpyxl 编写常规公式的简单网格。是的，这意味着总共有约 75 个公式（3 个表 × 每个 25 个单元格），但这很直接且是必需的。
+
+**Programmatic Population with Formulas:**
+
+每个敏感性表必须用公式完全填充，为每种假设组合重新计算 implied share price。**Do not use Excel's Data Table feature**（它需要手动干预，且无法通过 openpyxl 自动化）。
+
+**Implementation approach - CONCRETE EXAMPLE:**
+
+**Table Structure — 5×5 grid (ODD dimensions, base case centered):**
+
+如果模型的 base WACC = 9.0% 且 base terminal growth = 3.0%，请围绕这些值对称地构建坐标轴：
+
+```csv
+WACC vs Terminal Growth,  2.0%,  2.5%,  3.0%,  3.5%,  4.0%
+              8.0%,       [fml], [fml], [fml], [fml], [fml]
+              8.5%,       [fml], [fml], [fml], [fml], [fml]
+              9.0%,       [fml], [fml], [★  ], [fml], [fml]   ← middle row = base WACC
+              9.5%,       [fml], [fml], [fml], [fml], [fml]
+             10.0%,       [fml], [fml], [fml], [fml], [fml]
+                                   ↑
+                          middle col = base terminal g
+```
+
+**★ = the center cell.** 它的公式输出必须等于模型的实际 implied share price（来自估值汇总）。对这个单元格应用中蓝色填充（`#BDD7EE`）和粗体字体，使 base case 在视觉上得以锚定。
+
+**Rule for axis values:** `axis_values = [base - 2*step, base - step, base, base + step, base + 2*step]` — 围绕基准值对称，奇数数量保证有一个中心。
+
+**Formula Pattern - Cell B88 (WACC=8.0%, Terminal Growth=2.0%):**
+
+B88 中的公式应重新计算使用以下参数的 implied price：
+- WACC from row header: `$A88` (8.0%)
+- Terminal Growth from column header: `B$87` (2.0%)
+
+**推荐 approach:** Reference the main DCF calculation but substitute these values.
+
+**示例 formula structure:**
+`=([SUM of PV FCFs using $A88 as discount rate] + [Terminal Value using B$87 as growth rate and $A88 as WACC] - [Net Debt]) / [Shares]`
+
+**CRITICAL - Write a formula for EVERY cell in the 5x5 grid (25 cells per table, 75 cells total).** 使用 openpyxl 在循环中以编程方式编写这些公式。不要跳过此步骤或留下占位符文本。
+
+**Python implementation pattern:**
+```python
+# Pseudocode for populating sensitivity table
+for row_idx, wacc_value in enumerate(wacc_range):
+    for col_idx, term_growth_value in enumerate(term_growth_range):
+        # Build formula that uses wacc_value and term_growth_value
+        formula = f"=<DCF recalc using {wacc_value} and {term_growth_value}>"
+        ws.cell(row=start_row+row_idx, column=start_col+col_idx).value = formula
+```
+
+**The sensitivity tables must work immediately when the model is opened, with no manual steps required from the user.**
+
+</correct_patterns>
+
+<common_mistakes>
+
+本节包含了构建 DCF 模型时应避免的所有错误模式。
+
+### WRONG: Simplified Sensitivity Table Approximations or Placeholder Text
+
+**Don't use linear approximations:**
+
+```
+// WRONG - Linear approximation
+B97: =B88*(1+(0.096-0.116))    // Assumes linear relationship
+
+// WRONG - Division shortcut
+B105: =B88/(1+(E48-0.07))      // Doesn't recalculate full DCF
+```
+
+**Don't leave placeholder text:**
+```
+// WRONG - Placeholder note
+"Note: Use Excel Data Table feature (Data → What-If Analysis → Data Table) to populate sensitivity tables."
+
+// WRONG - Empty cells
+[leaving cells blank because "this is complex"]
+```
+
+**Don't confuse terminology:**
+- ❌ "Sensitivity tables need Excel's Data Table feature" (NO - that's a specific Excel tool we can't use)
+- ✅ "Sensitivity tables are simple grids with formulas in each cell" (YES - this is what we build)
+
+**Why these shortcuts are wrong:**
+- Linear approximation formulas don't actually recalculate the DCF - they just apply simple math adjustments
+- The relationships are not linear, so the results will be inaccurate
+- Placeholder text requires manual user intervention
+- Model is not immediately usable when delivered
+- Not professional or client-ready
+- Empty cells = incomplete deliverable
+
+**Common rationalization to REJECT:**
+"Writing 75+ formulas feels complex, so I'll leave a note for the user to complete it manually."
+
+**Reality:** 在 Python 中使用 openpyxl 循环时，编写 75 个公式很简单。每个公式遵循相同的模式 — 只需替换行/列值即可。这是交付物中必不可少的一部分。
+
+**Instead:** Populate every sensitivity cell with formulas that recalculate the full DCF for that specific combination of assumptions
+
+### WRONG: Missing Cell Comments
+
+**Don't do this:**
+- Create all hardcoded inputs without comments
+- Think "I'll add them later"
+- Write "TODO: add source"
+- Leave blue inputs without documentation
+
+**Why it's wrong:**
+- Can't verify where data came from
+- Fails xlsx skill requirements
+- Not audit-ready
+- Wastes time fixing later
+
+**Instead:** Add cell comment AS EACH hardcoded value is created
+
+### WRONG: Formula Row 参考资料 Off
+
+**Symptom:**
+FCF 部分引用了错误的假设行：
+`D&A:  =E29*$E$34    // Should be $E$21, but referencing wrong row`
+`CapEx: =E29*$E$41   // Should be $E$22, but row shifted`
+
+**Why this happens:**
+1. Formulas written first
+2. Then headers inserted
+3. All row references shifted
+4. Now formulas point to wrong cells → #REF! errors
+
+**Instead:** Lock row layout FIRST, then write formulas
+
+### WRONG: Single Row for Each Assumption Across Scenarios
+
+**Don't structure assumptions like this:**
+```csv
+Assumption,Bear,Base,Bull
+Revenue Growth FY1,10%,13%,16%
+Revenue Growth FY2,9%,12%,15%
+```
+这种垂直布局使得难以查看每个场景内跨年份的进展。
+
+**Why it's wrong:**
+- Makes it difficult to see assumptions evolving across years within each scenario
+- Harder to compare scenario assumptions across full projection period
+- Less intuitive for reviewing scenario logic
+
+**Instead:**
+- Create separate blocks for each scenario (Bear, Base, Bull)
+- Within each block, show assumptions horizontally across projection years
+- This makes each scenario's assumptions easier to review as a cohesive set
+
+### WRONG: No Borders
+
+**Don't deliver a model without borders:**
+- No section delineation
+- All cells blend together
+- Hard to read and unprofessional
+
+**Why it's wrong:**
+- Not client-ready
+- Difficult to navigate
+- Looks amateur
+
+**Instead:** Add borders around all major sections
+
+### WRONG: Wrong Font Colors or No Font Color Distinction
+
+**Don't do this:**
+- All text is black
+- Only use fill colors (no font color changes)
+- Mix up which cells are blue vs black
+
+**Why it's wrong:**
+- Can't distinguish inputs from formulas
+- Auditing becomes impossible
+- Violates xlsx skill requirements
+
+**Instead:** Blue text for ALL hardcoded inputs, black text for ALL formulas, green for sheet links
+
+### WRONG: Operating Expenses Based on Gross Profit
+
+**Don't do this:**
+`S&M: =E33*0.15    // E33 = Gross Profit (WRONG)`
+
+**Why it's wrong:**
+- Operating expenses scale with revenue, not gross profit
+- Produces unrealistic margin progression
+- Not how businesses actually operate
+
+**Instead:**
+`S&M: =E29*0.15    // E29 = Revenue (CORRECT)`
+
+### TOP 5 ERRORS SUMMARY
+
+1. **Formula row references off** → 在编写公式之前定义所有行位置
+2. **Missing cell comments** → 在创建单元格时添加注释，而不是在最后
+3. **Simplified sensitivity tables** → 用完整的 DCF 重新计算公式填充所有单元格，而不是近似值
+4. **Scenario block references wrong** → 确保 IF 公式从正确的 Bear/Base/Bull 块中提取
+5. **No borders** → 添加专业的章节边框以呈现可供客户使用的外观
+
+此外，请注意以下错误：
+
+### WACC Calculation Errors
+- Mixing book and market values in capital structure
+- Using equity beta instead of asset/unlevered beta incorrectly
+- Wrong tax rate application to cost of debt
+- Incorrect risk-free rate (must use current 10Y Treasury)
+- Failure to adjust for net debt vs net cash position
+
+### Growth Assumption Flaws
+- Terminal growth > WACC (creates infinite value)
+- Projection growth rates inconsistent with historical performance
+- Ignoring industry growth constraints
+- Revenue growth not aligned with unit economics
+- Margin expansion without operational justification
+
+### Terminal Value Mistakes
+- Using wrong growth method (perpetuity vs exit multiple)
+- Terminal value >80% of enterprise value (suggests over-reliance)
+- Inconsistent terminal margins with steady state assumptions
+- Wrong discount period for terminal value
+
+### Cash Flow Projection Errors
+- Operating expenses based on gross profit instead of revenue
+- D&A/CapEx percentages misaligned with business model
+- Working capital changes not properly calculated
+- Tax rate inconsistency between years
+- NOPAT calculation errors
+
+**These errors are the most common. Re-read this section before starting any DCF build.**
+
+</common_mistakes>
+
+## Excel File Creation
+
+**这个 skill 使用 `xlsx` skill 进行所有电子表格操作。** xlsx skill 提供：
+- 标准化的公式构建规则
+- 数字格式约定
+- 通过 `recalc.py` 脚本进行自动公式重新计算
+- 全面的错误检查和验证
+
+此 skill 创建的所有 Excel 文件必须遵循 xlsx skill 要求，包括零公式错误和正确的重新计算。
+
+## Quality Rubric
+
+每个 DCF 模型都必须最大化：
+1. 基于历史表现的 **真实营收和 margin 假设**
+2. 使用正确 CAPM 方法的 **适当的 cost of capital 计算**
+3. 显示估值范围的 **全面的敏感性分析**
+4. 带有支持性理由的 **清晰的终值计算**
+5. 支持场景分析的 **专业模型结构**
+6. 所有关键假设的 **透明的文档记录**
+
+## 输入 要求
+
+### Minimum 必需 输入
+1. **Company identifier**: Ticker symbol 或公司名称
+2. **Growth assumptions**: 预测期的营收增长率（或 "use consensus"）
+3. **可选 parameters**:
+   - Projection period (default: 5 years)
+   - Scenario cases (Bear/Base/Bull growth and margin assumptions)
+   - Terminal growth rate (default: 2.5-3.0%)
+   - Specific WACC inputs if not using CAPM
+
+## Excel Model Structure
+
+### Sheet Architecture
+
+创建 **两个工作表**：
+
+1. **DCF** - 主估值模型，底部包含敏感性分析
+2. **WACC** - Cost of capital 计算
+
+**CRITICAL**: 敏感性表位于 DCF 表的底部（而不是在单独的工作表上）。这使得所有估值输出保持在一起。
+
+### Formula Recalculation (MANDATORY)
+
+创建或修改 Excel 模型后，使用 `excel-author` skill 中的 `recalc.py` 脚本 **重新计算所有公式**：
+
+```bash
+python recalc.py [path_to_excel_file] [timeout_seconds]
+```
+
+示例:
+```bash
+python recalc.py AAPL_DCF_Model_2025-10-12.xlsx 30
+```
+
+该脚本将：
+- 使用 LibreOffice 重新计算所有工作表中的所有公式
+- 扫描所有单元格以查找 Excel 错误 (#REF!, #DIV/0!, #VALUE!, #NAME?, #NULL!, #NUM!, #N/A)
+- 返回包含错误位置和计数的详细 JSON
+
+**Expected output format:**
+```json
+{
+  "status": "success",           // or "errors_found"
+  "total_errors": 0,              // Total error count
+  "total_formulas": 42,           // Number of formulas in file
+  "error_summary": {}             // Only present if errors found
+}
+```
+
+**If errors are found**, 输出将包含详细信息：
+```json
+{
+  "status": "errors_found",
+  "total_errors": 2,
+  "total_formulas": 42,
+  "error_summary": {
+    "#REF!": {
+      "count": 2,
+      "locations": ["DCF!B25", "DCF!C25"]
+    }
+  }
+}
+```
+
+**Fix all errors** 并在交付模型之前重新运行 recalc.py，直到状态为 "success"。
+
+### 格式 Standards
+
+**IMPORTANT**: 对于公式构建规则和数字格式约定，请遵循 xlsx skill。DCF skill 增加了特定的视觉呈现标准。
+
+**Color Scheme - Two Layers**:
+
+**Layer 1: Font Colors (MANDATORY from xlsx skill)**
+- **Blue text (RGB: 0,0,255)**: 所有硬编码输入（股价、股数、历史数据、假设）
+- **Black text (RGB: 0,0,0)**: 所有公式和计算
+- **Green text (RGB: 0,128,0)**: 指向其他工作表的链接（WACC 表引用）
+
+**Layer 2: Fill Colors — Professional Blue/Grey Palette (默认 unless user specifies otherwise)**
+- **Keep it minimal** — 填充只使用蓝色和灰色。不要引入绿色、黄色、橙色或多种强调色。一个有太多颜色的模型看起来很业余。
+- **默认 fill palette:**
+  - **Section headers**: 深蓝色 (RGB: 31,78,121 / `#1F4E79`) 背景，白色粗体文本
+  - **Sub-headers/column headers**: 浅蓝色 (RGB: 217,225,242 / `#D9E1F2`) 背景，黑色粗