Skills › Financial Services › audit-xls
audit-xls
The facts
Its description
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".
The description the agent reads to decide when to use it.
From its settingsline 3
When it starts
A person working in a spreadsheet asks the agent to check formulas or hunt down errors, or reports that a model won't balance or that something seems off. The agent picks it up for spreadsheet QA, formula debugging, and financial-model integrity checks.
Things a person might say (the model's guesses)
- “Can you audit this sheet before I send it to the client?”
- “My model won't balance — can you figure out why?”
- “Something's off in my model, can you sanity check the formulas?”
A model's summary of when it is used.
A model's reading
What leads to it
- earnings-reviewer calls this earnings-reviewer, line 22
- gl-reconciler calls this gl-reconciler, line 33
- model-builder calls this after the model is built model-builder, line 22
- month-end-closer calls this month-end-closer, line 30
- pitch-agent calls this pitch-agent, line 23
- statement-auditor calls this statement-auditor, line 30
Other skills that hand off to this one, call it, require it or offer it instead, as a model read them.
A model's reading
Licence
Apache-2.0, from LICENSE
The terms its author shares it under, which let it be shown here.
From the repositorylicence text
The text
1---
2name: audit-xls
3description: Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".
4---
6# Audit Spreadsheet
8Audit formulas and data for accuracy and mistakes. Scope determines depth — from quick formula checks on a selection up to full financial-model integrity audits.
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.
Raw lines 1 to 910## Step 1: Determine scope
12If the user already gave a scope, use it. Otherwise **ask them**:
14> What scope do you want me to audit?
15> - **selection** — just the currently selected range
16> - **sheet** — the current active sheet only
17> - **model** — the whole workbook, including financial-model integrity checks (BS balance, cash tie-out, roll-forwards, logic sanity)
19The **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.
21---
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.
Raw lines 10 to 22
23## Step 2: Formula-level checks (ALL scopes)
25Run these regardless of scope:
27| Check | What to look for |
28|---|---|
29| Formula errors | `#REF!`, `#VALUE!`, `#N/A`, `#DIV/0!`, `#NAME?` |
30| Hardcodes inside formulas | `=A1*1.05` — the `1.05` should be a cell reference |
31| Inconsistent formulas | A formula that breaks the pattern of its neighbors in a row/column |
32| Off-by-one ranges | `SUM`/`AVERAGE` that misses the first or last row |
33| Pasted-over formulas | Cell that looks like a formula but is actually a hardcoded value |
34| Circular references | Intentional or accidental |
35| Broken cross-sheet links | References to cells that moved or were deleted |
36| Unit/scale mismatches | Thousands mixed with millions, % stored as whole numbers |
37| Hidden rows/tabs | Could contain overrides or stale calculations |
39---
Step 2: Formula-level checks (ALL scopes)
Run these regardless of scope:
| Check | What 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 formulas | A formula that breaks the pattern of its neighbors in a row/column |
| Off-by-one ranges | SUM/AVERAGE that misses the first or last row |
| Pasted-over formulas | Cell that looks like a formula but is actually a hardcoded value |
| Circular references | Intentional or accidental |
| Broken cross-sheet links | References to cells that moved or were deleted |
| Unit/scale mismatches | Thousands mixed with millions, % stored as whole numbers |
| Hidden rows/tabs | Could contain overrides or stale calculations |
Raw lines 23 to 40
41## Step 3: Model-integrity checks (MODEL scope only)
43If scope is **model**, identify the model type (DCF / LBO / 3-statement / merger / comps / custom) and run the appropriate integrity checks below.
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.
Raw lines 41 to 4445### 3a. Structural review
47| Check | What to look for |
48|---|---|
49| Input/formula separation | Are inputs clearly separated from calculations? |
50| Color convention | Blue=input, black=formula, green=link — or whatever the model uses, applied consistently? |
51| Tab flow | Logical order (Assumptions → IS → BS → CF → Valuation)? |
52| Date headers | Consistent across all tabs? |
53| Units | Consistent (thousands vs millions vs actuals)? |
3a. Structural review
| Check | What to look for |
|---|---|
| Input/formula separation | Are inputs clearly separated from calculations? |
| Color convention | Blue=input, black=formula, green=link — or whatever the model uses, applied consistently? |
| Tab flow | Logical order (Assumptions → IS → BS → CF → Valuation)? |
| Date headers | Consistent across all tabs? |
| Units | Consistent (thousands vs millions vs actuals)? |
55### 3b. Balance Sheet
57| Check | Test |
58|---|---|
59| BS balances | Total Assets = Total Liabilities + Equity (every period) |
60| RE rollforward | Prior RE + Net Income − Dividends = Current RE |
61| Goodwill/intangibles | Flow from acquisition assumptions (if M&A) |
63If BS doesn't balance, **quantify the gap per period and trace where it breaks** — nothing else matters until this is fixed.
3b. Balance Sheet
| Check | Test |
|---|---|
| BS balances | Total Assets = Total Liabilities + Equity (every period) |
| RE rollforward | Prior RE + Net Income − Dividends = Current RE |
| Goodwill/intangibles | Flow 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.
Raw lines 55 to 6465### 3c. Cash Flow Statement
67| Check | Test |
68|---|---|
69| Cash tie-out | CF Ending Cash = BS Cash (every period) |
70| CF sums | CFO + CFI + CFF = Δ Cash |
71| D&A match | D&A on CF = D&A on IS |
72| CapEx match | CapEx on CF matches PP&E rollforward on BS |
73| WC changes | Signs match BS movements (ΔAR, ΔAP, ΔInventory) |
3c. Cash Flow Statement
| Check | Test |
|---|---|
| Cash tie-out | CF Ending Cash = BS Cash (every period) |
| CF sums | CFO + CFI + CFF = Δ Cash |
| D&A match | D&A on CF = D&A on IS |
| CapEx match | CapEx on CF matches PP&E rollforward on BS |
| WC changes | Signs match BS movements (ΔAR, ΔAP, ΔInventory) |
75### 3d. Income Statement
77| Check | Test |
78|---|---|
79| Revenue build | Ties to segment/product detail |
80| Tax | Tax expense = Pre-tax income × tax rate (allow for deferred tax adj) |
81| Share count | Ties to dilution schedule (options, converts, buybacks) |
3d. Income Statement
| Check | Test |
|---|---|
| Revenue build | Ties to segment/product detail |
| Tax | Tax expense = Pre-tax income × tax rate (allow for deferred tax adj) |
| Share count | Ties to dilution schedule (options, converts, buybacks) |
83### 3e. Circular references
85- Interest → debt balance → cash → interest is a common intentional circ in LBO/3-stmt models
86- If intentional: verify iteration toggle exists and works
87- If unintentional: trace the loop and flag how to break it
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
89### 3f. Logic & reasonableness
91| Check | Flag if |
92|---|---|
93| Growth rates | >100% revenue growth without explanation |
94| Margins | Outside industry norms |
95| Terminal value dominance | TV > ~75% of DCF EV (yellow flag) |
96| Hockey-stick | Projections ramp unrealistically in out-years |
97| Compounding | EBITDA compounds to absurd $ by Year 10 |
98| Edge cases | Model breaks at 0% or negative growth, negative EBITDA, leverage goes negative |
3f. Logic & reasonableness
| Check | Flag if |
|---|---|
| Growth rates | >100% revenue growth without explanation |
| Margins | Outside industry norms |
| Terminal value dominance | TV > ~75% of DCF EV (yellow flag) |
| Hockey-stick | Projections ramp unrealistically in out-years |
| Compounding | EBITDA compounds to absurd $ by Year 10 |
| Edge cases | Model breaks at 0% or negative growth, negative EBITDA, leverage goes negative |
100### 3g. Model-type-specific bugs
102**DCF:**
103- Discount rate applied to wrong period (mid-year vs end-of-year)
104- Terminal value not discounted back
105- WACC uses book values instead of market values
106- FCF includes interest expense (should be unlevered)
107- Tax shield double-counted
109**LBO:**
110- Debt paydown doesn't match cash sweep mechanics
111- PIK interest not accruing to principal
112- Management rollover not reflected in returns
113- Exit multiple applied to wrong EBITDA (LTM vs NTM)
114- Fees/expenses not deducted from Day 1 equity
116**Merger:**
117- Accretion/dilution uses wrong share count (pre- vs post-deal)
118- Synergies not phased in
119- Purchase price allocation doesn't balance
120- Foregone interest on cash not included
121- Transaction fees not in sources & uses
123**3-statement:**
124- Working capital changes have wrong sign
125- Depreciation doesn't match PP&E schedule
126- Debt maturity schedule doesn't match principal payments
127- Dividends exceed net income without explanation
129---
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
Raw lines 100 to 130
131## Step 4: Report
133Output a findings table:
135| # | Sheet | Cell/Range | Severity | Category | Issue | Suggested Fix |
136|---|---|---|---|---|---|---|
138**Severity:**
139- **Critical** — wrong output (BS doesn't balance, formula broken, cash doesn't tie)
140- **Warning** — risky (hardcodes, inconsistent formulas, edge-case failures)
141- **Info** — style/best-practice (color coding, layout, naming)
143For **model** scope, prepend a summary line:
145> Model type: [DCF/LBO/3-stmt/...] — Overall: [Clean / Minor Issues / Major Issues] — [N] critical, [N] warnings, [N] info
147**Don't change anything without asking** — report first, fix on request.
149---
Step 4: Report
Output a findings table:
| # | Sheet | Cell/Range | Severity | Category | Issue | Suggested 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.
Raw lines 131 to 150
151## Notes
153- **BS balance first** — if it doesn't balance, everything downstream is suspect
154- **Hardcoded overrides are the #1 source of silent bugs** — search aggressively
155- **Sign convention errors** (positive vs negative for cash outflows) are extremely common
156- If the model uses VBA macros, note any macro-driven calculations that can't be audited from formulas alone
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
From anthropics/financial-services at 6056506, 2026-10-28. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.