Skip to content

charlieviettq/awesome-agent-skill / .claude/skills/data-financial-analysis

"data-financial-analysis"

Verified

"Interpret the three core financial statements (income statement, balance sheet, cash flow statement) to assess business health and performance. Use this skill when the user needs to read financial statements, understand profitability vs cash flow, evaluate a company's financial position, or prepare for investor/board meetings — even if they say 'explain these financials', 'are we making money', 'read this annual report', or 'what do these numbers mean'.".

FileKindSize
SKILL.mdskill md4.3 KB
examples/sample_scenario.mdmarkdown5.2 KB

examples/sample_scenario.md

View on GitHub
# Example: 台灣 SaaS 新創 CloudMesh Inc. FY2024 財務健康診斷

## Scenario

CloudMesh Inc. 是一家台灣上市的 B2B SaaS 公司(主要提供供應鏈協作平台),CFO 準備下週的董事會報告。她把 FY2024 年報丟給 Claude,問:「我們這一年看起來營收成長很快,但現金老是不夠用,董事會一定會問這個問題,幫我解釋這份財報的真實狀況。」

財報數字(TIFRS,單位:百萬 TWD):

**損益表(FY2024 vs FY2023)**
- 營業收入:480 vs 320(+50%)
- 毛利:312 vs 208(毛利率 65% vs 65%)
- 營業費用:290 vs 195
- 營業利益:22 vs 13(+69%)
- 淨利:18 vs 11

**資產負債表(12/31/2024 vs 12/31/2023)**
- 應收帳款:144 vs 64
- 存貨:0(純 SaaS)
- 總資產:680 vs 420
- 短期借款:80 vs 20
- 長期負債:120 vs 60
- 股東權益:310 vs 260

**現金流量表(FY2024)**
- 營業活動現金流:-28
- 投資活動現金流:-95(資本支出 -40,開發成本資本化 -55)
- 籌資活動現金流:+110(新增借款 +120,股利 -10)
- 期末現金:42(期初現金 55)

---

## Analysis

### Step 1:損益表 — 表面上很亮眼

- 營收 +50%,毛利率維持 65%(定價能力穩健,SaaS COGS 控制良好)
- 但費用比率:FY2024 費用/營收 = 290/480 = **60%**,FY2023 = 195/320 = **61%** → 費用規模化效應很微弱
- 營業利益率:22/480 = **4.6%**(去年 4.1%)→ 雖有改善,SaaS 公司在此階段通常期待更快的槓桿效應
- **初步判斷**:盈利存在,但利潤擴張不如營收增速

### Step 2:資產負債表 — 槓桿快速攀升

| 指標 | FY2024 | FY2023 |
|------|--------|--------|
| D/E 比(總負債/股東權益) | 1.19 | 0.62 |
| 流動比率(估) | 約 1.2 | 約 1.8 |
| 應收帳款週轉天數 | 144/480×365 = **109 天** | 64/320×365 = **73 天** |

- 應收帳款從 64M 跳到 144M,增幅 **125%**,遠超營收增速 50%
- **帳款週轉天數從 73 天惡化到 109 天** → 客戶付款變慢,或業務端在衝季末合約
- 負債結構:短期借款從 20M → 80M,長期負債從 60M → 120M,總借款 **200M**(去年 80M)

### Step 3:現金流量表 — 問題核心在這裡

| 項目 | FY2024 |
|------|--------|
| 營業活動現金流 | **-28M**(虧損) |
| 資本支出(硬體、機房) | -40M |
| 開發成本資本化 | -55M |
| 自由現金流 | **-68M** |
| 靠借款填洞 | +120M |

- 淨利 +18M,但營業現金流 **-28M**:兩者差了 46M
- 差距解釋:應收帳款增加 80M(現金還沒收到)是主要元兇
- 開發成本資本化 55M:需確認是否符合 TIFRS IAS 38 資本化標準,否則有美化利潤之嫌
- **核心問題:CloudMesh 的成長是靠借債,不是靠自己賺出來的現金**

### Step 4:跨報表交叉驗證

| 訊號 | 數據 | 警示 |
|------|------|------|
| 營收 +50%,營業 CF 從正轉負 | 收入認列但現金未收 | 🔴 應收帳款品質待確認 |
| 淨利 +18M vs 營業 CF -28M | 差距 46M | 🔴 Accrual 驅動獲利 |
| 開發成本全部資本化 55M | 若費用化則淨利約 -37M | 🟡 會計政策影響大 |
| 借款 +120M 撐現金 | 若信貸收緊則流動性風險 | 🔴 財務彈性降低 |

---

## Result

```markdown
# Financial Statement Analysis: CloudMesh Inc. — FY2024

## Income Statement Highlights
| Metric | FY2024 | FY2023 | Change |
|--------|--------|--------|--------|
| Revenue | $480M | $320M | +50% |
| Gross Margin | 65% | 65% | 0 pp |
| Operating Margin | 4.6% | 4.1% | +0.5 pp |
| Net Income | $18M | $11M | +64% |

## Balance Sheet Highlights
| Metric | FY2024 | FY2023 |
|--------|--------|--------|
| Total Assets | $680M | $420M |
| Total Debt | $200M | $80M |
| D/E Ratio | 1.19x | 0.62x |
| AR Days Outstanding | 109 天 | 73 天 |

## Cash Flow Highlights
| Category | Amount |
|----------|--------|
| Operating CF | -$28M |
| Investing CF | -$95M |
| Financing CF | +$110M |
| Free Cash Flow | -$68M |

## Red Flags
- 應收帳款週轉天數惡化 36 天(+49%),增速遠超營收成長,現金回收能力下滑
- 淨利 +18M vs 營業現金流 -28M,差距 46M 幾乎完全來自未收現的應收帳款
- 開發成本資本化 55M 需確認 IAS 38 合規性;若應費用化,FY2024 實際為虧損
- 總借款一年內翻 2.5 倍(80M → 200M),D/E 從 0.62 升至 1.19,財務槓桿風險上升
- 公司現金靠融資而非營運支撐,若市場信貸條件收緊,流動性將承壓

## Overall Assessment
**財務健康:警示黃燈(需立即追蹤應收帳款與資本化政策)**

CloudMesh 的 50% 營收成長是真實的,毛利率穩定顯示 SaaS 定價能力健全。
但「有利潤、無現金」的結構需正視:核心問題是應收帳款惡化(客戶付款週期拉長),
導致帳面獲利無法轉換為現金。公司目前靠借款填補現金缺口,此路徑不可持續。

**董事會應追問的三個問題:**
1. 應收帳款中有多少超過 90 天未收?主要客戶的付款行為有無改變?
2. 開發成本資本化的具體項目為何?是否通過 IAS 38 技術可行性測試?
3. FY2025 是否有明確路徑使營業現金流轉正,或有備用信用額度支應流動性需求?
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall