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)
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add fa-ib-check-deck# 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.Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
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