Skip to content
Agentmart
Submit a tool

equity-valuation

股票估值报告引擎 — 数据质量门控/多方法估值/质量评估/风险矩阵/决策框架的 Excel 完整估值工作簿

Skill by claude-office-skills

IndexedMIT★ 9
Write a review

Chalk Labs

Need help deploying equity-valuation?

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-equity-valuation

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

股票估值报告引擎 — 数据质量门控/多方法估值/质量评估/风险矩阵/决策框架的 Excel 完整估值工作簿

Use cases: spreadsheets

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/equity-valuation

What's inside

Skill name
equity-valuation
Description
股票估值报告引擎 — 数据质量门控/多方法估值/质量评估/风险矩阵/决策框架的 Excel 完整估值工作簿
License
MIT
Instructions
197 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## 股票估值报告引擎(决策级完整工作簿)

当用户要求"给这只股票估值"/"值不值得买"/"对比 A 和 B"/"写投资备忘录"时,你生成的是**包含完整估值逻辑链的多 Sheet Excel 工作簿** — 从数据验证到最终投资结论,每步可审计、可调参。

本 Skill 与 `financial-modeling` 配合使用:`financial-modeling` 负责 DCF/P&L 的具体公式实现,本 Skill 负责**估值决策框架和报告结构**。

---

### 工作簿结构(7 个 Sheet)

| # | Sheet 名称 | 核心内容 |
|---|-----------|---------|
| 1 | 数据总览 | 数据源/日期/质量评分/置信度等级 |
| 2 | 核心假设 | Bull/Base/Bear 三情景参数面板 |
| 3 | 相对估值 | P/E / P/B / EV/EBITDA 同行对比表 |
| 4 | DCF 模型 | FCF预测 + 折现 + 终端价值(调用 financial-modeling 规范) |
| 5 | 质量评估 | 6维企业质量打分矩阵 |
| 6 | 风险矩阵 | 风险事件 × 概率 × 影响 × 监控触发器 |
| 7 | 估值结论 | 三角验证 + 安全边际 + 投资结论仪表盘 |

---

### Sheet 1:数据总览与质量门控

这是模型的"入口检查"——先验证数据质量再做估值:

```javascript
// 数据质量评分(公式驱动)
// 完整性得分 = 已填字段数 / 总必填字段数
ws.Range("C8").Formula = "=COUNTA(C12:C25)/14";
ws.Range("C8").NumberFormat = "0%";

// 时效性标记
ws.Range("C9").Value2 = "2024-12-31";  // 最新财报期(蓝色可编辑)
ws.Range("D9").Formula = '=IF(TODAY()-DATEVALUE(C9)>180,"⚠ 超过6个月","✓ 近期")';

// 置信度等级(自动判断)
ws.Range("C10").Formula = '=IF(C8>=0.85,"High",IF(C8>=0.6,"Medium","Low"))';
// High = 可做完整估值三角验证
// Medium = 可估值但需加宽区间
// Low = 仅定性方向判断,跳过精确 DCF

// 必填数据清单(缺失项红色标记)
var fields = ["收入(TTM)","净利润","EBITDA","总资产","总负债",
  "股东权益","经营现金流","CapEx","总股数","当前股价",
  "Beta","行业","同行公司","最近分红"];
```

**关键规则**:如果置信度为 Low,自动跳过 DCF Sheet,仅生成相对估值 + 质量评估 + 定性结论。

---

### Sheet 3:相对估值表

```javascript
// 表头
var headers = ["公司","P/E(TTM)","P/E(Fwd)","P/B","EV/EBITDA","EV/Sales","ROE","股息率"];

// 目标公司行(从数据总览引用)
// 同行公司行(用户提供或AI建议3-5家)
// 行业中位数行 = MEDIAN 公式

// 隐含价值列(每个倍数一列)
ws.Range("I5").Formula = "=MEDIAN(B6:B10)*'数据总览'!$C$17";  // 隐含P/E价值

// 折溢价标记(条件格式)
// 低于中位数 10%+ → 绿色  |  高于中位数 10%+ → 红色  |  区间内 → 无色

// 估值评分
ws.Range("I12").Formula = '=COUNTIF(I5:I9,">"&\'数据总览\'!$C$20)/5';
// 高于当前股价的方法数占比 → 越高越"便宜"
```

---

### Sheet 5:质量评估矩阵(6 维度)

```javascript
var dimensions = [
  { name: "护城河与定价权",   weight: 0.20 },
  { name: "治理与资本配置",   weight: 0.15 },
  { name: "盈利质量(现金转化)", weight: 0.20 },
  { name: "资产负债风险",     weight: 0.15 },
  { name: "周期性与外部依赖",  weight: 0.15 },
  { name: "执行力与历史兑现",  weight: 0.15 }
];

// 每维度: 评分(1-5) + 证据描述 + 权重
// 综合质量分 = 加权平均
ws.Range("E12").Formula = "=SUMPRODUCT(C5:C10,D5:D10)";
// 1-2 = Weak | 3 = Neutral | 4-5 = Strong

// 评分为蓝色可编辑(Font.Color = 0xFF0000)
// 权重也可调
```

---

### Sheet 6:风险矩阵

```javascript
// 结构: 风险事件 | 类别 | 概率(1-5) | 影响(1-5) | 风险分 | 监控触发器 | 状态
// 风险分 = 概率 × 影响(公式)
ws.Range("E5").Formula = "=C5*D5";

// 前置填充常见风险类别
var riskCategories = ["宏观/政策","行业竞争","执行/管理","财务/流动性","估值/市场情绪","ESG/合规"];

// 风险热力图配色(条件格式)
// 风险分 >= 15 → 红色 | 10-14 → 橙色 | 5-9 → 黄色 | < 5 → 绿色
```

---

### Sheet 7:估值结论仪表盘

这是整个工作簿的"一页纸摘要":

```javascript

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)
Feb 28, 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 equity-valuation 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 equity-valuation?

CallGet help
Cite this page

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