Agent skill

Three-Statement Financial Analysis

by HKUDS in HKUDS/Vibe-Trading

Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text.

MITAuto-check passedBusiness, Finance & HR

SKILL.md written in Chinese; this summary is our English description.

Install Three-Statement Financial Analysis

skills CLI
$ npx skills add HKUDS/Vibe-Trading --skill financial-statement -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/Vibe-Trading financial-statement --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/financial-statement .claude/skills/financial-statement && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
financial-statement
GitHub stars
35k
Token cost
~1.2k tokens
SKILL.md length
203 words
Files
1
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text.

  • Works in 6 steps: 财报会计准则差异:A股用中国会计准则,港股/美股用IFRS/US… → 季度数据看同比非环比:季节性因素大(如消费Q4旺季),环比波动不代表趋势 → 银行/保险特殊:三表结构与一般企业完全不同,不适用传统勾稽分析 → …
  • Checking whether reported profit is backed by operating cash flow
  • SKILL.md covers 概述, 三表核心框架, 三表勾稽关系 and 盈利质量分析, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill starts from how the three statements tie together: net profit flows into retained earnings, receivables reflect revenue not yet collected, and cash flow shows what was actually received. It gives key ratios with healthy ranges and warnings for each statement, and a matrix that reads the signs of operating, investing and financing cash flow to classify a company as excellent, expanding, stable, dangerous, distressed or declining. The instructions are written in Chinese.

Earnings quality is checked by comparing accruals with cash flow, using an accrual ratio and a weighted scorecard that covers cash flow to net profit, receivables growth against revenue growth, recurring profit share, operating cash flow trend and inventory turnover. A table of 12 red flags includes high cash alongside high debt, surging receivables, negative operating cash flow with positive profit and frequent auditor changes, each with a detection method and severity. A DuPont breakdown of ROE rounds out the framework.

When your agent uses it

  • Checking whether reported profit is backed by operating cash flow
  • Screening a company for financial manipulation red flags
  • Breaking ROE into margin, turnover and equity multiplier with DuPont analysis
  • Reading how the three statements reconcile with one another

Example prompts

  • “Calculate the accrual ratio and CFO to net profit for this company and rate its earnings quality.”
  • “Check this annual report against the 12 financial red flags and count how many are triggered.”
  • “Do a DuPont breakdown of ROE for the last three years.”
  • “Classify the company's cash flow pattern from the signs of its CFO, CFI and CFF.”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 财报会计准则差异:A股用中国会计准则,港股/美股用IFRS/US GAAP,比较时注意调整
  2. 季度数据看同比非环比:季节性因素大(如消费Q4旺季),环比波动不代表趋势
  3. 银行/保险特殊:三表结构与一般企业完全不同,不适用传统勾稽分析
  4. 重资产 vs 轻资产:资产周转率跨行业不可比,同行业内比较才有意义
  5. 并表范围变化:新收购/处置子公司导致同比不可比,需看可比口径
  6. 数据来源:tushare提供A股财报数据,extra_fields中可获取pe/pb/roe等指标

What it can do on your machine

Read from SKILL.md and the folder at commit e532650. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Three-Statement Financial Analysis loads about 1.2k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit e532650, republished under its MIT licence (© HKUDS). 203 words, ~1,217 tokens.

Download SKILL.mdSave it as .claude/skills/financial-statement/SKILL.md (or your agent's skills folder).
name
financial-statement
description
财报三表深度解读——三表勾稽关系、盈利质量(应计vs现金流)分析、杜邦分解、10+财务造假红旗指标
category
flow

财报三表解读

概述

从三张报表(利润表、资产负债表、现金流量表)的勾稽关系出发,深度分析企业盈利质量,识别财务造假信号,用杜邦分析分解盈利驱动因子。

三表核心框架

利润表(赚了多少)
营业收入
 - 营业成本               → 毛利润(毛利率 = 毛利/营收)
 - 销售费用 + 管理费用 + 研发费用  → 核心利润
 + 投资收益 + 公允价值变动        → 营业利润
 + 营业外收支               → 利润总额
 - 所得税                 → 净利润
 - 少数股东损益              → 归母净利润

关键比率:

比率公式健康范围警示
毛利率毛利/营收行业差异大连续3季下滑
净利率净利/营收>10%优秀<0%且无改善趋势
期间费用率(销管研)/营收<30%逐年上升
扣非/归母扣非净利/归母净利>80%<50%依赖非经常
资产负债表(有什么家底)
资产 = 负债 + 所有者权益

资产端重点:
- 货币资金: 是否受限?存贷双高?
- 应收账款: 增速是否超过营收?
- 存货: 是否积压?跌价准备够不够?
- 商誉: 并购溢价,减值风险
- 在建工程: 是否长期不转固?

负债端重点:
- 有息负债: 短期借款+长期借款+应付债券
- 应付账款: 对上游议价权
- 预收/合同负债: 对下游议价权

关键比率:

比率公式健康范围
资产负债率负债/资产40-60%(非金融)
流动比率流动资产/流动负债1.5-2.5
速动比率(流动资产-存货)/流动负债>1.0
有息负债率有息负债/总资产<30%
现金流量表(真正拿到多少现金)
经营活动现金流(CFO): 做生意赚的现金
投资活动现金流(CFI): 买卖资产花的现金
筹资活动现金流(CFF): 借钱/还钱/分红

黄金公式: 净利润 ≈ CFO(长期来看)

现金流质量矩阵:

CFOCFICFF企业状态
+--优秀(赚钱、投资、还债)
+-+扩张(赚钱、投资、借钱加速)
++-稳健(赚钱、回收投资、还债)
--+危险(亏钱、还在投、靠借钱活)
-++困境(卖资产+借钱维持)
-+-衰退(卖资产还债)

三表勾稽关系

核心勾稽
1. 利润表 → 资产负债表
   净利润 → 留存收益(未分配利润增加)
   应收增加 = 收入 - 实际收款
   存货增加 = 采购 - 已售成本

2. 利润表 → 现金流量表
   净利润 + 折旧 - 营运资本增加 ≈ 经营现金流
   如果差异大 → 盈利质量存疑

3. 资产负债表 → 现金流量表
   期末现金 = 期初现金 + CFO + CFI + CFF
   货币资金变动 = 三个现金流之和
勾稽验证公式
python
# 验证盈利质量
accrual_ratio = (net_income - cfo) / total_assets
# accrual_ratio > 10% → 应计利润占比高,盈利质量差

# 验证收入质量
receivable_growth = accounts_receivable.pct_change(fill_method=None)
revenue_growth = revenue.pct_change(fill_method=None)
# receivable_growth > revenue_growth → 收入质量恶化

# 验证资产负债表与现金流一致性
cash_change = cash_end - cash_begin
cf_total = cfo + cfi + cff
# abs(cash_change - cf_total) > 1 → 数据有问题

盈利质量分析

应计 vs 现金流
高质量盈利:
- CFO / 净利润 > 1.0(现金利润大于纸面利润)
- 应收账款增速 < 营收增速
- 经营现金流持续为正

低质量盈利:
- CFO / 净利润 < 0.5(大量利润没变成现金)
- 应收/营收比例持续上升
- 依赖一次性收益(投资收益、资产处置)
盈利质量评分卡
指标优秀(3分)一般(2分)差(1分)权重
CFO/净利润>1.20.8-1.2<0.825%
应收增速vs营收应收增速更慢同步应收更快20%
扣非/归母>90%70-90%<70%20%
经营现金流趋势连续增长波动下降20%
存货周转加快稳定放慢15%

评分 ≥ 2.5 = 盈利质量优秀 评分 1.5-2.5 = 需要关注 评分 < 1.5 = 盈利质量差,建议回避

财务造假红旗指标

12个红旗信号
#红旗检测方法严重度
1存贷双高货币资金高 + 有息负债高(同时>营收30%)高
2应收暴增应收增速 > 营收增速 × 1.5,持续2季+高
3存货异常存货/营收比例突然上升>50%高
4经营现金流为负CFO连续2年为负但净利润为正高
5关联交易占比高关联交易/营收 > 30%高
6频繁更换审计师3年内换2次审计师中
7在建工程不转固在建工程/固定资产 > 50%,持续3年+中
8预付账款异常预付/营收比例突然上升中
9少数股东损益异常少数股东损益/净利润比例波动大中
10审计意见非标准无保留意见(保留/否定/无法表示)高
11资本化率过高研发资本化/研发总额 > 50%中
12商誉占比高商誉/净资产 > 30%,且标的业绩不达标中
综合造假概率评估
红旗数量    造假概率    建议
0-1个       低          正常投资
2-3个       中          深入调查,谨慎投资
4-5个       高          建议回避
6+个        极高        强烈回避

杜邦分析

三级分解
ROE = 净利率 × 总资产周转率 × 权益乘数

ROE = (净利润/营收) × (营收/总资产) × (总资产/净资产)
     盈利能力        运营效率        杠杆水平
五级分解
ROE = 税务负担 × 利息负担 × 营业利润率 × 资产周转率 × 权益乘数
    = (净利/税前利润) × (税前利润/EBIT) × (EBIT/营收) × (营收/总资产) × (总资产/净资产)
杜邦分析模板
markdown
### 杜邦分析: [公司名]

| 指标 | 2024 | 2025 | 变化 | 驱动判断 |
|------|------|------|------|---------|
| ROE | 15.2% | 17.8% | +2.6% | ↑ |
| 净利率 | 8.5% | 9.2% | +0.7% | 盈利改善 ✓ |
| 资产周转率 | 0.85 | 0.88 | +0.03 | 效率提升 ✓ |
| 权益乘数 | 2.10 | 2.20 | +0.10 | 杠杆上升 ⚠️ |

结论: ROE提升主要由盈利能力改善驱动,杠杆小幅上升需关注
行业ROE对比
行业典型ROE驱动类型
白酒25-30%高净利率驱动(毛利率>90%)
零售8-15%高周转驱动(薄利多销)
银行10-14%高杠杆驱动(权益乘数>10x)
科技12-20%高净利率+中等周转
地产5-10%高杠杆但在去杠杆

输出格式

markdown
## 财务分析: [公司名/代码]

### 三表概要
| 指标 | 2023A | 2024A | 2025E | 趋势 |
|------|-------|-------|-------|------|
| 营收(亿) | ... | ... | ... | ... |
| 净利润(亿) | ... | ... | ... | ... |
| CFO(亿) | ... | ... | ... | ... |
| 资产负债率 | ... | ... | ... | ... |

### 盈利质量评分
| 指标 | 得分 | 说明 |
|------|------|------|
| CFO/净利润 | 3/3 | 1.25, 现金回收优秀 |
| ... | ... | ... |
| **综合** | **2.7/3** | **盈利质量优秀** |

### 杜邦分解
[杜邦分析表格]

### 红旗检查
- [x] 存贷双高 → 否,货币资金合理
- [x] 应收异常 → 否,增速低于营收
- [!] 商誉占比 → 22%,接近警戒线,需关注

### 结论
...

注意事项

  1. 财报会计准则差异:A股用中国会计准则,港股/美股用IFRS/US GAAP,比较时注意调整
  2. 季度数据看同比非环比:季节性因素大(如消费Q4旺季),环比波动不代表趋势
  3. 银行/保险特殊:三表结构与一般企业完全不同,不适用传统勾稽分析
  4. 重资产 vs 轻资产:资产周转率跨行业不可比,同行业内比较才有意义
  5. 并表范围变化:新收购/处置子公司导致同比不可比,需看可比口径
  6. 数据来源:tushare提供A股财报数据,extra_fields中可获取pe/pb/roe等指标

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agent/src/skills/financial-statement of HKUDS/Vibe-Trading.

Open the folder on GitHubat commit e532650

Compare with similar skills

Three-Statement Financial Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Three-Statement Financial Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Three-Statement Financial Analysis this skillHKUDS/Vibe-Trading35k—~1.2kAutomated safety check: PassMIT
Finance Opsericosiu/ai-marketing-skills3.6k1 repos~1.4kAutomated safety check: PassMIT
Longbridge Earningshelsome/folio2701 repos~2.5kAutomated safety check: PassNone
Financial Analyzinghuangjia2019/claude-code-engineering1.1k—~474Automated safety check: PassNone
Earnings AnalysisWind-Alice/AliceMarket1303 repos~2.2kAutomated safety check: PassNone
Buy Side Equity Research Memohaskaomni/serenity-skill633—~3.8kAutomated safety check: PassMIT

Similar skills

  • Finance Ops

    ericosiu/ai-marketing-skills

    AI-powered financial analysis suite. An agent skill from ericosiu/ai-marketing-skills.

    3.6k GitHub starsUsed in 1 repo~1.4k tokens
    Business, Finance & HRAuto-check passed
  • Longbridge Earnings

    helsome/folio

    Earnings analysis — pre- and post-earnings. An agent skill from helsome/folio.

    270 GitHub starsUsed in 1 repo~2.5k tokens
    Business, Finance & HRAuto-check passed
  • Financial Analyzing

    huangjia2019/claude-code-engineering

    Analyze financial data, calculate financial ratios, and generate analysis reports.

    1.1k GitHub stars~474 tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Earnings Analysis

    Wind-Alice/AliceMarket

    Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage.

    130 GitHub starsUsed in 3 repos~2.2k tokens
    Business, Finance & HRAuto-check passed
  • Buy Side Equity Research Memo

    haskaomni/serenity-skill

    Generate source-backed buy-side equity research memos from a ticker, starting with investment view, target-price scenarios, SEC and IR-backed financial statement analysis, industry chain…

    633 GitHub stars~3.8k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Financial Research

    firecrawl/web-agent

    Pulls a public company's latest 10-K or 10-Q figures and analyst consensus from SEC EDGAR and Yahoo Finance, then cross-checks the two sources.

    1.2k GitHub stars~1.1k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed

More from HKUDS/Vibe-Trading

All 89 skills in this repo
  • Eastmoney Market Data

    HKUDS/Vibe-Trading

    Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.

    35k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • OKX Market Data

    HKUDS/Vibe-Trading

    Retrieves public OKX cryptocurrency market data such as spot prices, candlesticks, funding rates and open interest through the OKX V5 REST API, with no authentication.

    35k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • SEC EDGAR Filings Fetcher

    HKUDS/Vibe-Trading

    Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.

    35k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • A-Share ST Risk Screener

    HKUDS/Vibe-Trading

    Predicts whether a mainland China A-share company risks an ST or *ST warning after its next annual report, using financial thresholds and Sina penalty records.

    35k GitHub stars~4.9k tokensUpdated today
    Auto-check passed
  • Breaks a structural trend such as AI infrastructure into its physical supply chain and ranks lesser-known listed companies sitting on each bottleneck.

    35k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Plans and drafts an eight-part, roughly 120k-word investigative series on one company, built around a strict fact-check pass rather than fast drafting.

    35k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Questions about Three-Statement Financial Analysis

What does Three-Statement Financial Analysis do?

Reads the income statement, balance sheet and cash flow statement together to judge earnings quality, apply DuPont analysis and check 12 red-flag indicators for manipulation; Chinese text. The skill starts from how the three statements tie together: net profit flows into retained earnings, receivables reflect revenue not yet collected, and cash flow shows what was actually received. It gives key ratios with healthy ranges and warnings for each statement, and a matrix that reads the signs of operating, investing and financing cash flow to classify a company as excellent, expanding, stable, dangerous, distressed or declining.

When should I use Three-Statement Financial Analysis?

Three-Statement Financial Analysis fits situations like: checking whether reported profit is backed by operating cash flow; screening a company for financial manipulation red flags; breaking ROE into margin, turnover and equity multiplier with DuPont analysis; reading how the three statements reconcile with one another.

How do I install Three-Statement Financial Analysis in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill financial-statement -a claude-code`. Or copy the skill folder (agent/src/skills/financial-statement in HKUDS/Vibe-Trading) into .claude/skills/financial-statement in your project. Claude Code loads it when a task matches its description.

How do I install Three-Statement Financial Analysis in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill financial-statement -a codex`. Or copy the skill folder (agent/src/skills/financial-statement in HKUDS/Vibe-Trading) into .agents/skills/financial-statement in your project. Codex loads it when a task matches its description.

Can I use Three-Statement Financial Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill financial-statement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/financial-statement, .gemini/skills/financial-statement, .github/skills/financial-statement and .opencode/skills/financial-statement in your project.

What does Three-Statement Financial Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Three-Statement Financial Analysis is instructions for the agent only.

Does Three-Statement Financial Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Three-Statement Financial Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Three-Statement Financial Analysis use?

Three-Statement Financial Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Three-Statement Financial Analysis use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Three-Statement Financial Analysis?

Skills that share tags, products or a category with Three-Statement Financial Analysis: Finance Ops (ericosiu/ai-marketing-skills, 3.6k stars), Longbridge Earnings (helsome/folio, 270 stars), Financial Analyzing (huangjia2019/claude-code-engineering, 1.1k stars) and Earnings Analysis (Wind-Alice/AliceMarket, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Three-Statement Financial Analysis?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,043 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 8, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.