anthropics/financial-services

audit-xls

Audit a spreadsheet for formula accuracy, errors, and common mistakes.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/anthropics/financial-services --skill audit-xls

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Audit Spreadsheet

Audit formulas and data for accuracy and mistakes. Scope determines depth — from quick formula checks on a selection up to full financial-model integrity audits.

Step 1: Determine scope

If the user already gave a scope, use it. Otherwise ask them:

What scope do you want me to audit? - selection — just the currently selected range - sheet — the current active sheet only - model — the whole workbook, including financial-model integrity checks (BS balance, cash tie-out, roll-forwards, logic sanity)

The model scope is the deepest — use it for DCF, LBO, 3-statement, merger, comps, or any integrated financial model before sending to a client or IC.


Step 2: Formula-level checks (ALL scopes)

Run these regardless of scope:

CheckWhat to look for
Formula errors#REF!, #VALUE!, #N/A, #DIV/0!, #NAME?
Hardcodes inside formulas=A1*1.05 — the 1.05 should be a cell reference
Inconsistent formulasA formula that breaks the pattern of its neighbors in a row/column
Off-by-one rangesSUM/AVERAGE that misses the first or last row
Pasted-over formulasCell that looks like a formula but is actually a hardcoded value
Circular referencesIntentional or accidental
Broken cross-sheet linksReferences to cells that moved or were deleted
Unit/scale mismatchesThousands mixed with millions, % stored as whole numbers
Hidden rows/tabsCould contain overrides or stale calculations

Step 3: Model-integrity checks (MODEL scope only)

If scope is model, identify the model type (DCF / LBO / 3-statement / merger / comps / custom) and run the appropriate integrity checks below.

3a. Structural review

CheckWhat to look for
Input/formula separationAre inputs clearly separated from calculations?
Color conventionBlue=input, black=formula, green=link — or whatever the model uses, applied consistently?
Tab flowLogical order (Assumptions → IS → BS → CF → Valuation)?
Date headersConsistent across all tabs?
UnitsConsistent (thousands vs millions vs actuals)?

3b. Balance Sheet

CheckTest
BS balancesTotal Assets = Total Liabilities + Equity (every period)
RE rollforwardPrior RE + Net Income − Dividends = Current RE
Goodwill/intangiblesFlow from acquisition assumptions (if M&A)

If BS doesn't balance, quantify the gap per period and trace where it breaks — nothing else matters until this is fixed.

3c. Cash Flow Statement

CheckTest
Cash tie-outCF Ending Cash = BS Cash (every period)
CF sumsCFO + CFI + CFF = Δ Cash
D&A matchD&A on CF = D&A on IS
CapEx matchCapEx on CF matches PP&E rollforward on BS
WC changesSigns match BS movements (ΔAR, ΔAP, ΔInventory)

3d. Income Statement

CheckTest
Revenue buildTies to segment/product detail
TaxTax expense = Pre-tax income × tax rate (allow for deferred tax adj)
Share countTies to dilution schedule (options, converts, buybacks)

3e. Circular references

  • Interest → debt balance → cash → interest is a common intentional circ in LBO/3-stmt models
  • If intentional: verify iteration toggle exists and works
  • If unintentional: trace the loop and flag how to break it

3f. Logic & reasonableness

CheckFlag if
Growth rates>100% revenue growth without explanation
MarginsOutside industry norms
Terminal value dominanceTV > ~75% of DCF EV (yellow flag)
Hockey-stickProjections ramp unrealistically in out-years
CompoundingEBITDA compounds to absurd $ by Year 10
Edge casesModel breaks at 0% or negative growth, negative EBITDA, leverage goes negative

3g. Model-type-specific bugs

DCF:

  • Discount rate applied to wrong period (mid-year vs end-of-year)
  • Terminal value not discounted back
  • WACC uses book values instead of market values
  • FCF includes interest expense (should be unlevered)
  • Tax shield double-counted

LBO:

  • Debt paydown doesn't match cash sweep mechanics
  • PIK interest not accruing to principal
  • Management rollover not reflected in returns
  • Exit multiple applied to wrong EBITDA (LTM vs NTM)
  • Fees/expenses not deducted from Day 1 equity

Merger:

  • Accretion/dilution uses wrong share count (pre- vs post-deal)
  • Synergies not phased in
  • Purchase price allocation doesn't balance
  • Foregone interest on cash not included
  • Transaction fees not in sources & uses

3-statement:

  • Working capital changes have wrong sign
  • Depreciation doesn't match PP&E schedule
  • Debt maturity schedule doesn't match principal payments
  • Dividends exceed net income without explanation

Step 4: Report

Output a findings table:

#SheetCell/RangeSeverityCategoryIssueSuggested Fix

Severity:

  • Critical — wrong output (BS doesn't balance, formula broken, cash doesn't tie)
  • Warning — risky (hardcodes, inconsistent formulas, edge-case failures)
  • Info — style/best-practice (color coding, layout, naming)

For model scope, prepend a summary line:

Model type: [DCF/LBO/3-stmt/...] — Overall: [Clean / Minor Issues / Major Issues] — [N] critical, [N] warnings, [N] info

Don't change anything without asking — report first, fix on request.


Notes

  • BS balance first — if it doesn't balance, everything downstream is suspect
  • Hardcoded overrides are the #1 source of silent bugs — search aggressively
  • Sign convention errors (positive vs negative for cash outflows) are extremely common
  • If the model uses VBA macros, note any macro-driven calculations that can't be audited from formulas alone

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
anthropics
公式

equity-research

Generate comprehensive equity research snapshots combining analyst consensus estimates, company fundamentals, historical prices, and macroeconomic context. Use when researching stocks, comparing estimates to actuals, analyzing company financials, assessing equity valuations, or building investment cases.

1時間の導入数
1
GitHub Stars
4.1万
更新日
11月12日
anthropics
公式

bond-relative-value

Perform relative value analysis on bonds by combining pricing, yield curve context, credit spreads, and scenario stress testing. Use when analyzing bond richness/cheapness, computing spread decomposition, comparing bonds, assessing bond value vs curves, or running rate shock scenarios.

1時間の導入数
1
GitHub Stars
4.1万
更新日
11月12日
anthropics
公式

comps-analysis

Build institutional-grade comparable company analyses with operating metrics, valuation multiples, and statistical benchmarking in Excel/spreadsheet format. Perfect for: - Public company valuation (M&A, investment analysis) - Benchmarking performance vs. industry peers - Pricing IPOs or funding rounds - Identifying valuation outliers (over/under-valued) - Supporting investment committee presentations - Creating sector overview reports Not ideal for: - Private companies without comparable public

1時間の導入数
1
GitHub Stars
4.1万
更新日
11月12日
anthropics
公式

dcf-model

Real DCF (Discounted Cash Flow) model creation for equity valuation. Retrieves financial data from SEC filings and analyst reports, builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models with executive summaries. Use when users need to value a company using DCF methodology, request intrinsic value analysis, or ask for detailed financial modeling with growth projections and terminal value calculations.

1時間の導入数
1
GitHub Stars
4.1万
更新日
11月12日