Investment Banking Deck Quality Checker
Comprehensive QC review of pitch decks and client presentations covering number consistency, data-narrative alignment, language polish, and visual formatting.
Sending a pitch deck with conflicting numbers on different slides — or a chart that contradicts the narrative two pages earlier — is the kind of mistake that erodes client trust instantly and is almost impossible to catch on a fifth read-through at midnight.
Who it's for: investment banking analysts, associates, VPs, management consultants, anyone preparing client-ready financial presentations
Example
"Check this pitch deck before we send it to the client" → Severity-rated QC report: 2 Critical issues (revenue mismatch between slides 3 and 15, chart data contradicting narrative), 4 Important issues (missing source citations, terminology inconsistency), 3 Minor issues (font size drift, date format)
New here? 3-minute setup guide → | Already set up? Copy the template below.
# IB Deck Checker
Perform comprehensive QC on the presentation across four dimensions. Read every slide, then report findings.
## Environment check
This skill works in both the PowerPoint add-in and chat. Identify which you're in before starting:
- **Add-in** — read from the live open deck.
- **Chat** — read from the uploaded `.pptx` file.
This is read-and-report only — no edits — so the workflow is identical in both.
## Workflow
### Read the deck
Pull text from every slide, keeping track of which slide each line came from. You'll need slide-level attribution for every finding ("$500M appears on slides 3 and 8, but slide 15 shows $485M"). A deck with 30 slides is too much to hold in working memory reliably — write the extracted text to a file so the number-checking script can process it.
The script expects markdown-ish input with slide markers. Format as:
```
## Slide 1
[slide 1 text content]
## Slide 2
[slide 2 text content]
```
### 1. Number consistency
Run the extraction script on what you collected:
```bash
python scripts/extract_numbers.py /tmp/deck_content.md --check
```
It normalizes units ($500M vs $500MM vs $500,000,000 → same number), categorizes values (revenue, EBITDA, multiples, margins), and flags when the same metric category shows conflicting values on different slides. This is the part most likely to catch something a human missed on the fifth read-through.
Beyond what the script flags, verify:
- Calculations are correct (totals sum, percentages add up, growth rates match the endpoints)
- Unit style is consistent — the deck should pick one of $M or $MM and stick with it
- Time periods are aligned — FY vs LTM vs quarterly, explicitly labeled
### 2. Data-narrative alignment
Map claims to the data that's supposed to support them. This is where decks go wrong quietly — someone edits the chart on slide 7 and forgets the narrative on slide 4.
- Trend statements ("declining margins") → does the chart actually go that direction?
- Market position claims ("#1 player") → revenue and share data support it?
- Plausibility — "#1 in a $100B market" with $200M revenue is 0.2% share; that's not #1
### 3. Language polish
IB decks have a register. Scan for anything that breaks it: casual phrasing ("pretty good", "a lot of"), contractions, exclamation points, vague quantifiers without numbers, inconsistent terminology for the same concept.
See `references/ib-terminology.md` for replacement patterns.
### 4. Visual and formatting QC
Run standard visual verification checks on each slide. You're looking for: missing chart source citations, missing axis labels, typography inconsistencies, number formatting drift (1,000 vs 1K within the same deck), date format drift, footnote and disclaimer gaps.
Visual verification catches overlaps, overflow, and contrast issues that don't show up in text extraction. Don't skip it — a chart with no source citation looks the same as a properly sourced one in the text dump.
## Output
Use `references/report-format.md` as the structure. Categorize by severity:
- **Critical** — number mismatches, factual errors, data contradicting narrative. These block client delivery.
- **Important** — language, missing sources, terminology drift. Should fix.
- **Minor** — font sizes, spacing, date formats. Polish.
Lead with criticals. If there aren't any, say so explicitly — "no number inconsistencies found" is a finding, not an absence of one.
What This Does
Performs comprehensive quality control on investment banking presentations across four dimensions: number consistency across slides, data-narrative alignment, language polish against IB standards, and visual/formatting QC. Produces a severity-rated report that separates client-delivery blockers from polish items.
Quick Start
Step 1: Create a Project Folder
Create a folder for your deck review and place the downloaded template inside as CLAUDE.md.
Step 2: Download the Template
Click Download above, then move the file into your project folder as CLAUDE.md.
Step 3: Start Working
"Check this pitch deck for number consistency and errors before client delivery"
"QC this management presentation — reconcile figures across all slides"
"Final review pass on this CIM — is it client-ready?"
Four QC Dimensions
1. Number Consistency
Normalizes units ($500M vs $500MM vs $500,000,000), categorizes values by type (revenue, EBITDA, multiples, margins), and flags conflicting values across slides. Also verifies calculations, unit style consistency, and time period alignment (FY vs LTM vs quarterly).
2. Data-Narrative Alignment
Maps claims to supporting data. Catches cases where someone edited a chart but forgot the narrative — "declining margins" with a chart showing margins going up, or "#1 player" claims that the revenue data does not support.
3. Language Polish
Scans for anything that breaks IB register: casual phrasing ("pretty good", "a lot of"), contractions, exclamation points, vague quantifiers without numbers, and inconsistent terminology for the same concept.
4. Visual and Formatting QC
Checks for missing chart source citations, missing axis labels, typography inconsistencies, number formatting drift (1,000 vs 1K), date format drift, and footnote/disclaimer gaps.
Severity Levels
| Level | Definition | Example |
|---|---|---|
| Critical | Number mismatches, factual errors, data contradicting narrative. Blocks client delivery. | Revenue shows $500M on slide 3 but $485M on slide 15 |
| Important | Language issues, missing sources, terminology drift. Should fix. | Chart missing source citation |
| Minor | Font sizes, spacing, date formats. Polish items. | Inconsistent date format across slides |
Tips & Best Practices
- This is a read-and-report workflow — no edits are made to the deck, only findings reported
- The tool catches issues that manual review typically misses: variant number formats, stale derived values, and chart data that does not match the narrative
- Run this as a final pass after all content edits are complete
- "No number inconsistencies found" is a finding, not an absence of one — the report explicitly confirms clean areas