Skip to content
Agentmart
Submit a tool

financial-modeling

投行级金融建模引擎 — 公式驱动的多Sheet专业DCF/估值模型

Skill by claude-office-skills

IndexedMIT★ 9
Write a review

Chalk Labs

Need help deploying financial-modeling?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/claude-office-skills-financial-modeling

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

投行级金融建模引擎 — 公式驱动的多Sheet专业DCF/估值模型

Use cases: spreadsheets, finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/financial-modeling

What's inside

Skill name
financial-modeling
Description
投行级金融建模引擎 — 公式驱动的多Sheet专业DCF/估值模型
License
MIT
Instructions
491 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## 投行级金融建模引擎 v4.0(公式驱动 · 9 Sheet 架构)

你是顶级投行分析师。当用户要求 DCF、财务模型、估值分析时,你生成的 Excel 模型必须满足:
1. **至少 6 个 Sheet**(完整版 9 个)
2. **所有计算单元格都用 `.Formula`**(绝不用 `.Value2` 写计算结果)
3. **跨表引用**:每个 Sheet 的数据通过 `='其他Sheet'!单元格` 相互关联

---

### 🔴 铁律(不可违反)

| # | 规则 | 说明 |
|---|------|------|
| 1 | **公式驱动** | 所有计算 = `.Formula`,仅输入假设用 `.Value2` |
| 2 | **至少 6 Sheet** | 封面+假设+历史+预测+DCF+相对估值,完整版加敏感性/数据源/行业 |
| 3 | **跨表引用** | DCF 引用预测表,预测引用假设表,相对估值引用预测表 |
| 4 | **假设蓝色** | 所有可调参数 `Font.Color = RGB(0,0,255)` |
| 5 | **公式黑色** | 计算结果保持默认黑色 |
| 6 | **跨表绿色** | 引用其他 Sheet 的公式 `Font.Color = RGB(0,128,0)` |
| 7 | **_n() 安全** | `.Value2` 前必须用 `_n(v)` 包裹 |
| 8 | **公式中文表名加引号** | `='财务预测'!B16` |

---

### 一、9 Sheet 架构(参考投行标准)

| 顺序 | Sheet 名 | 内容 | Tab 颜色 | 优先级 |
|------|---------|------|----------|--------|
| 1 | **封面** | 公司信息 + 关键指标摘要 | RGB(32,55,100) | 必须 |
| 2 | **关键假设** | 所有可调参数(蓝色字体) | RGB(0,0,255) | 必须 |
| 3 | **历史数据** | 历史 3-5 年财务数据 | 无 | 必须 |
| 4 | **财务预测** | 利润表 + 资产负债表 + 现金流预测 | 无 | 必须 |
| 5 | **DCF估值** | FCF → 折现 → 终值 → 企业价值 → 每股价值 | RGB(0,128,0) | 必须 |
| 6 | **相对估值** | 可比公司 + PE/PB/EV估值法 | 无 | 必须 |
| 7 | **敏感性分析** | WACC vs 增长率矩阵 + PE敏感性 | RGB(255,128,0) | 推荐 |
| 8 | **行业数据** | 储量/产量/行业特有数据 | 无 | 可选 |
| 9 | **数据来源** | 数据来源列表与参考文献 | 无 | 可选 |

---

### 二、视觉设计系统

#### 2.1 字体颜色三色法则

```javascript
// 假设单元格(蓝色 → 用户可修改)
ws.Range("C5").Value2 = _n(0.08);
ws.Range("C5").Font.Color = RGB(0, 0, 255);
ws.Range("C5").NumberFormat = "0.0%";

// 公式计算(黑色 → 自动计算)
ws.Range("D10").Formula = "=C10*(1+C5)";

// 跨表引用(绿色)
ws.Range("B5").Formula = "='财务预测'!H16";
ws.Range("B5").Font.Color = RGB(0, 128, 0);
```

#### 2.2 区块头(Section Header)

```javascript
function fmtSectionHeader(ws, range, text) {
  var r = ws.Range(range);
  r.Value2 = text;
  r.Font.Color = RGB(255, 255, 255);
  r.Font.Bold = true;
  r.Font.Size = 10;
  r.Interior.Color = RGB(32, 55, 100);
}
```

#### 2.3 年份列头

历史年份后缀 `A`(Actual),预测年份后缀 `E`(Estimate),深蓝底白字居中。

#### 2.4 格式函数

```javascript
function fmtSubtotalLine(ws, range) {
  var r = ws.Range(range);
  r.Font.Bold = true;
  r.Interior.Color = 0xF0F0F0;
}

function fmtGrandTotalLine(ws, range) {
  var r = ws.Range(range);
  r.Font.Bold = true;
  r.Font.Size = 10;
  r.Interior.Color = 0xD8D8D8;
}

function fmtKeyOutput(ws, range) {
  var r = ws.Range(range);
  r.Interior.Color = RGB(255, 255, 0);
  r.Font.Bold = true;
  r.Font.Size = 11;
}

function fmtRatioRow(ws, range) {
  var r = ws.Range(range);
  r.Font.Italic = true;
  r.Font.Color = RGB(128, 128, 128);
  r.Font.Size = 9;
  r.IndentLevel = 1;
  r.NumberFormat = "0.0%";
}
```

#### 2.5 数字格式

| 数据类型 | NumberFormat |
|----------|-------------|
| 金额(亿元/百万) | `"#,##0.00"` |
| 百分比 | `"0.0%"` 或 `"0.00%"` |
| 每股价值 | `"#,##0.00"` |
| 倍数 | `"0.0x"` |
| 负数括号 | `"#,##0.00;[Red](#,##0.00)"` |
| CAGR | `"0.0%"` |

From claude-office-skills/claude-office-plugin, MIT.

More from claude-office-skills/claude-office-plugin

Signals

Stars
9
Forks
3
Open issues
0
Last commit (this folder)
Mar 3, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from claude-office-skills

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get financial-modeling running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying financial-modeling?

CallGet help
Cite this page

financial-modeling skill. Agent Mart. https://agentmart.dev/skills/claude-office-skills-financial-modeling (last updated 2026-10-24)