Pitch Deck Reviewer

Pitch Deck Reviewer

Review a pitch deck with VC-grade rigor and produce a scored, actionable pitch-review.md.

Contents

• references/evaluation-framework.md -- The 8 scored dimensions, weights, red flags, scoring guides, design notes, and overall-score calculation.
• references/objections-and-benchmarks.md -- Investor objection categories and the canonical successful-deck benchmarks.
• references/output-template.md -- The exact pitch-review.md structure to generate.

Workflow

1. Ingest the deck. Determine file type and location, then read every slide. Supported inputs: PDF (Read directly; for 10+ pages read in batches via the pages parameter), PowerPoint .pptx (invoke the pptx skill or Read), Google Slides links (WebFetch if public), images PNG/JPG (Read to inspect visually), markdown/text descriptions, and directories of slide images (Glob to enumerate, then Read each). For .pen files, state that they cannot be read directly. 2. Build a slide inventory. Catalog each slide by number and primary content before any analysis. Identify company name, stage, and industry. Flag any deck over 20 slides as a concern itself; most successful decks run 10-15. 3. Score the 8 dimensions. Apply references/evaluation-framework.md. Score each 1-10 with specific evidence from the deck, then compute the weighted overall score and assign the grade label. 4. Write slide-by-slide feedback. Cover every slide with content summary, purpose, effectiveness, strengths, weaknesses, and recommendations. 5. Predict investor objections. Generate at least 5 using the categories in references/objections-and-benchmarks.md, each with severity, trigger, suggested verbal response, and deck fix. 6. Compare to benchmark decks. Reference at least 2 relevant decks from references/objections-and-benchmarks.md; name where this deck is stronger, weaker, and what to borrow. 7. Rank the top 5 improvements by impact and list any missing slides or sections for this stage and industry. 8. Assemble pitch-review.md per references/output-template.md. Write the executive summary last. Save it beside the source deck (or the working directory). Show the overall-score math.

Calibration

• Verify any market-size, revenue, or growth claim with WebSearch before accepting it. Never fabricate metrics, comparisons, or statistics.
• Reserve 9-10 on a dimension for work that sets a new standard. Give an overall below 3.0 only when the deck has almost no usable content.
• Adjust for stage: weight pre-product decks toward problem/solution clarity, team, and market; relax traction and financials expectations and note the calibration.
• Score absent major sections (e.g., missing financials or team) 1-2 and flag them in the executive summary and the missing-sections list. Review works in progress rather than refusing.
• Evaluate intentionally unconventional decks (memo-style, demo-first, single-page) on their own terms while noting the divergence from convention.
• For multiple versions, review the latest and note which changes improved the deck and which regressed.

Voice

• Be direct and specific. Replace vague praise with concrete observations.
• Pair every critique with a concrete fix.
• Use investor framing ("This raises a question about...") over verdicts ("This is bad").
• Acknowledge what works before identifying gaps. Define any jargon used.
• Write for the founder, to help them improve.

Evaluation Framework: The 8 Core Dimensions

Score each dimension on a scale of 1-10. Justify every score with specific evidence from the deck.

---

1. Narrative Flow and Story Arc (Weight: 15%)

Evaluate:

• Whether the deck follows a logical progression that builds conviction.
• Whether there is a clear story arc: setup, conflict, resolution, vision.
• Whether transitions between slides feel natural or jarring.
• Whether the deck maintains momentum or loses energy at any point.
• Whether there is emotional resonance alongside logical argumentation.

Benchmark structure (ideal order, not rigid): 1. Hook / Opening (grab attention in first 10 seconds) 2. Problem (make the pain visceral) 3. Solution (clear, specific, not vague) 4. Product / Demo (show, don't tell) 5. Traction / Validation (prove it works) 6. Market Size (show the prize) 7. Business Model (show how money flows) 8. Competition (honest positioning) 9. Team (why this team wins) 10. Financials (where the money goes) 11. The Ask (specific, justified) 12. Vision / Close (inspire)

Scoring guide:

• 9-10: Deck reads like a compelling story; each slide creates a reason to see the next
• 7-8: Solid flow with minor sequencing issues; one or two slides feel out of place
• 5-6: Adequate but mechanical; feels like a checklist rather than a narrative
• 3-4: Disjointed; significant logical gaps between sections
• 1-2: No coherent narrative; slides appear randomly ordered

---

2. Problem Definition and Solution Clarity (Weight: 15%)

Evaluate:

• Whether the problem is specific, measurable, and relatable.
• Whether the problem feels urgent and large enough to build a company around.
• Whether the solution is clearly connected to the problem.
• Whether the solution can be explained in one sentence after reading.
• Whether the value proposition is differentiated and defensible.
• Whether the solution avoids being a "vitamin" (nice to have) vs. a "painkiller" (must have).

Red flags:

• Problem described in abstract terms without concrete examples
• Solution that addresses a different problem than the one presented
• Multiple problems listed without clear prioritization
• Solution that requires lengthy explanation to understand
• No evidence that the target customer actually experiences this problem
• Problem framed around the founder's experience rather than market evidence

Scoring guide:

• 9-10: Problem makes you wince; solution is an obvious, elegant response
• 7-8: Problem is clear and real; solution is solid but could be sharper
• 5-6: Problem exists but feels generic; solution is one of many possible approaches
• 3-4: Problem is vague or niche; solution is unclear or overcomplicated
• 1-2: No convincing problem; solution looking for a problem

---

3. Market Sizing Methodology (Weight: 12%)

Evaluate:

• Whether the TAM/SAM/SOM framework is used correctly.
• Whether the market sizing is bottom-up (preferred) or top-down only.
• Whether the assumptions behind each number are explicit and defensible.
• Whether the SAM represents a realistic addressable portion.
• Whether the SOM is achievable within the funding horizon.
• Whether third-party sources are cited for market data.
• Whether the market shows a growth trajectory.

Bottom-up validation checklist:

• Number of potential customers identified
• Average revenue per customer estimated
• Geographic or segment scope defined
• Growth rate assumptions stated
• Sources cited for key figures

Red flags:

• TAM-only sizing without SAM/SOM breakdown
• "If we get just 1% of the market" reasoning
• Market size pulled from a single analyst report without validation
• Conflating adjacent markets to inflate TAM
• No distinction between current market and projected market
• Market size that does not match the product's actual addressable segment
• Outdated market data (more than 2 years old)

Scoring guide:

• 9-10: Rigorous bottom-up analysis with cited sources and clear assumptions
• 7-8: Solid sizing with minor gaps; assumptions mostly explicit
• 5-6: Top-down only but reasonable; some assumptions unclear
• 3-4: Inflated numbers with weak methodology; key assumptions missing
• 1-2: No market sizing or completely fabricated numbers

---

4. Competitive Positioning (Weight: 10%)

Evaluate:

• Whether real competitors are named (not just "traditional solutions").
• Whether the competitive landscape is honest and complete.
• Whether the differentiation is specific and defensible.
• Whether the moat grows over time (network effects, data, switching costs).
• Whether the positioning matrix is fair (not rigged to make the startup look perfect).
• Whether indirect competitors and substitutes are acknowledged.

Common positioning frameworks to check for:

• 2x2 matrix (most common; check if axes are meaningful and not cherry-picked)
• Feature comparison table (check for honesty in competitor columns)
• Value chain positioning (where in the stack does this sit?)
• Category creation argument (is this genuinely new or rebranding?)

Red flags:

• "We have no competitors" (always a red flag)
• Competitors listed are all small startups (ignoring incumbents)
• Positioning matrix with axes designed to guarantee the startup wins
• No mention of what happens when incumbents copy the feature
• Differentiation based solely on price (unsustainable)
• No discussion of switching costs or barriers to entry

Scoring guide:

• 9-10: Honest, complete landscape with defensible, lasting differentiation
• 7-8: Good awareness with clear differentiation; minor blind spots
• 5-6: Acknowledges competitors but differentiation is weak or temporary
• 3-4: Incomplete landscape; differentiation is superficial
• 1-2: Ignores competition or claims none exists

---

5. Financial Projections Realism (Weight: 12%)

Evaluate:

• Whether revenue projections are grounded in bottoms-up unit economics.
• Whether growth rates are defensible with comparable company benchmarks.
• Whether the cost structure is realistic (especially headcount and CAC).
• Whether key financial metrics are present (LTV, CAC, LTV:CAC ratio, payback period, gross margin).
• Whether the path to profitability or next funding round is clear.
• Whether assumptions are explicitly stated.

Unit economics checklist:

• Customer Acquisition Cost (CAC) -- how is it calculated?
• Lifetime Value (LTV) -- what assumptions drive this?
• LTV:CAC ratio -- is it above 3:1?
• Payback period -- how many months to recover CAC?
• Gross margin -- does it improve with scale?
• Churn rate -- is it realistic for the segment?
• Revenue per employee -- does it scale?

Red flags:

• Hockey stick revenue with no explanation of inflection point
• Year 3 revenue above $100M without clear path from current run rate
• CAC that decreases over time without explanation
• No churn assumptions in a subscription model
• Gross margins above 90% without justification
• Headcount that does not scale with revenue growth
• No sensitivity analysis or scenario planning
• Revenue projections that imply market share above 20% in year 3-5

Scoring guide:

• 9-10: Detailed model with explicit assumptions, benchmarked metrics, and scenario analysis
• 7-8: Solid projections with reasonable assumptions; minor gaps in unit economics
• 5-6: Projections present but assumptions unclear; optimistic but not absurd
• 3-4: Unrealistic growth or missing key metrics; assumptions unstated
• 1-2: No financials or completely detached from reality

---

6. Team Credibility (Weight: 12%)

Evaluate:

• Whether the team has relevant domain expertise for this specific problem.
• Whether there is a technical co-founder if the product is technical.
• Whether there are previous exits or notable company experience.
• Whether the team composition covers the key functions needed at this stage.
• Whether advisors or board members are relevant and active (not just name-dropping).
• Whether there is evidence of the team's ability to execute (prior traction).

Key roles to verify for stage:

• Pre-seed/Seed: Technical + Business co-founders minimum; domain expertise
• Series A: VP Engineering, Head of Sales/Growth, plus seed-stage roles
• Series B+: Full C-suite with relevant scaling experience

Red flags:

• Solo non-technical founder building a technical product
• All co-founders from same background (no diversity of skills)
• Team bios focused on education rather than relevant experience
• Advisory board with no skin in the game
• No evidence the founders have worked together before
• Key missing roles with no hiring plan mentioned
• Founder-market fit not articulated

Scoring guide:

• 9-10: Dream team with deep domain expertise, complementary skills, and track record
• 7-8: Strong team with relevant experience; one or two gaps with clear hiring plan
• 5-6: Adequate team but missing key expertise; founder-market fit unclear
• 3-4: Significant gaps; team has not demonstrated relevant capability
• 1-2: Team does not inspire confidence for this specific challenge

---

7. Ask Clarity and Use of Funds (Weight: 12%)

Evaluate:

• Whether the funding amount is specific and justified.
• Whether the use of funds is broken down by category with percentages.
• Whether the allocation aligns with the company's stated priorities.
• Whether the runway is clearly stated (months of operation this raise covers).
• Whether milestones are tied to the use of funds.
• Whether the valuation expectation is reasonable for the stage.

Typical allocation benchmarks (early stage):

• Engineering/Product: 40-60%
• Sales/Marketing: 20-30%
• Operations/G&A: 10-20%
• Reserve/Buffer: 5-10%

Red flags:

• No specific amount requested
• "We are raising $X" with no breakdown of how it will be spent
• Majority of funds going to non-core activities
• Runway less than 12 months (raises take time)
• No milestones or KPIs tied to the fundraise
• Valuation implied that is disconnected from traction
• Asking for too little (underfunding) or too much (unnecessary dilution)
• No mention of expected next raise timing or path to profitability

Scoring guide:

• 9-10: Specific ask with detailed allocation, clear milestones, and realistic timeline
• 7-8: Clear ask with reasonable allocation; milestones partially defined
• 5-6: Amount stated but allocation vague; milestones not tied to funds
• 3-4: Vague ask with no breakdown or unrealistic expectations
• 1-2: No ask stated or completely unjustified amount

---

8. Traction and Validation (Weight: 12%)

Evaluate:

• Whether metrics are current and specific (not "growing fast").
• Whether the growth rate is demonstrated with a time series, not just a snapshot.
• Whether vanity metrics are distinguished from meaningful ones.
• Whether there is evidence of product-market fit.
• Whether customer testimonials or logos are present and verifiable.
• Whether there is a clear trend line, not just cherry-picked data points.

Stage-appropriate traction expectations:

• Pre-seed: Problem validation interviews, LOIs, waitlist signups, prototype feedback
• Seed: Beta users, early revenue, pilot customers, engagement metrics
• Series A: $1M+ ARR, clear growth rate, unit economics, retention cohorts
• Series B+: Proven scalability, expanding margins, market leadership evidence

Meaningful metrics by business model:

• SaaS: MRR/ARR, net revenue retention, logo churn, expansion revenue
• Marketplace: GMV, take rate, liquidity (supply/demand balance), repeat usage
• Consumer: DAU/MAU ratio, retention curves, engagement depth, viral coefficient
• Hardware: Pre-orders, manufacturing margins, supply chain readiness

Red flags:

• Only showing cumulative charts (hides declining growth)
• Citing user signups without activation or engagement data
• Revenue figures without context (one-time vs. recurring)
• Testimonials without attribution
• Metrics from a period that ended months ago
• No cohort analysis for retention claims
• Impressive percentage growth on a tiny base

Scoring guide:

• 9-10: Comprehensive metrics dashboard with clear growth trajectory and retention proof
• 7-8: Strong metrics in key areas; minor gaps in supporting data
• 5-6: Some traction shown but lacks depth; metrics are surface-level
• 3-4: Minimal traction with cherry-picked highlights
• 1-2: No traction data or only vanity metrics

---

Design and Visual Communication (Unscored but Noted)

Design is not one of the 8 scored dimensions. Note significant design issues that impact communication:

• Slide density (too much text per slide)
• Font readability and consistency
• Color scheme professionalism
• Data visualization clarity
• Image quality and relevance
• Brand consistency across slides
• White space usage
• Slide count (ideal: 10-15 for a pitch meeting, up to 20 for a leave-behind)

---

Overall Score Calculation

Compute the weighted overall score using these weights:

Overall Score = Sum of (Dimension Score * Weight)

Grade thresholds:

• 9.0-10.0: Exceptional -- Ready to send to top-tier VCs as-is
• 8.0-8.9: Strong -- Minor refinements needed; competitive deck
• 7.0-7.9: Good -- Solid foundation but needs work in specific areas
• 6.0-6.9: Fair -- Fundamental improvements required before circulating
• 5.0-5.9: Needs Work -- Significant gaps; recommend major revision
• Below 5.0: Not Ready -- Requires complete overhaul before investor meetings

Investor Objection Prediction and Benchmark Decks

Investor Objection Prediction

Predict the top 5-10 objections an experienced investor would raise. For each objection, capture:

1. The Objection: State it exactly as an investor would phrase it in a partner meeting. 2. Why They Will Raise It: What specifically in the deck triggers this concern. 3. Severity: High / Medium / Low (how likely this kills the deal). 4. Suggested Response: How the founder should address this objection. 5. Deck Fix: What change to the deck could preempt this objection entirely.

Map each predicted objection to one of these categories:

• Market Risk: Is this market real, large enough, and growing?
• Execution Risk: Can this team build and ship this product?
• Technical Risk: Can the technology actually work at scale?
• Competitive Risk: What stops incumbents or well-funded competitors?
• Business Model Risk: Will the unit economics ever work?
• Timing Risk: Why now? Is the market ready?
• Regulatory Risk: Could regulation kill or constrain this?
• Capital Efficiency Risk: Is this a venture-scale return opportunity?

---

Comparison to Successful Decks

After completing the analysis, compare the reviewed deck to well-known successful pitch decks in the same or adjacent space.

Canonical Reference Decks

• Airbnb (2009): Clean problem/solution, market timing, simple business model
• Buffer (2011): Transparency, traction-led, clear metrics
• LinkedIn Series B: Network effects thesis, clear monetization strategy
• Mixpanel: Data-driven positioning, developer-focused GTM
• Intercom: Category creation, bottom-up adoption narrative
• Front (Series A): Team communication pain point, collaborative workflow
• Coinbase (Seed): Market timing thesis, regulatory awareness, trust positioning
• Uber (2008): Market sizing methodology, two-sided marketplace dynamics
• Sequoia pitch template: Problem, Solution, Why Now, Market, Competition, Product, Business Model, Team, Financials
• Y Combinator standard: Traction-first, demo-heavy, concise (under 12 slides)

How to Compare

For each comparison: 1. Identify the most relevant benchmark deck(s) based on industry, stage, and business model. 2. Note specific slides or sections where the reviewed deck is stronger or weaker. 3. Highlight techniques from successful decks that could be borrowed. 4. Call out structural or narrative elements that successful decks use that the reviewed deck is missing.

Be specific about what to borrow and how, not just "be more like Airbnb."

Output Template: pitch-review.md

Generate a file called pitch-review.md in the same directory as the source deck (or the working directory if no specific location is provided). Follow this exact structure.

# Pitch Deck Review: [Company Name]

**Review Date:** [Date]
**Deck Version:** [Filename or description]
**Stage:** [Pre-seed / Seed / Series A / Series B / etc.]
**Industry:** [Primary industry/vertical]
**Reviewer:** Claude Pitch Deck Reviewer

---

## Executive Summary

[3-5 sentence overview of the deck's strengths and weaknesses. Lead with the strongest element, then the most critical gap. End with the overall assessment of investor-readiness.]

**Overall Score: [X.X] / 10 -- [Grade Label]**

---

## Slide-by-Slide Analysis

### Slide [N]: [Slide Title or Description]

**Content Summary:** [What this slide contains]
**Purpose:** [What this slide is trying to accomplish]
**Effectiveness:** [How well it achieves that purpose]

**Strengths:**
- [Specific strength with evidence]

**Weaknesses:**
- [Specific weakness with evidence]

**Recommendations:**
- [Actionable, specific improvement]

[Repeat for every slide]

---

## Dimension Scores

| Dimension | Score | Weight | Weighted |
|---|---|---|---|
| Narrative Flow and Story Arc | [X]/10 | 15% | [X.XX] |
| Problem/Solution Clarity | [X]/10 | 15% | [X.XX] |
| Market Sizing Methodology | [X]/10 | 12% | [X.XX] |
| Competitive Positioning | [X]/10 | 10% | [X.XX] |
| Financial Projections Realism | [X]/10 | 12% | [X.XX] |
| Team Credibility | [X]/10 | 12% | [X.XX] |
| Ask Clarity and Use of Funds | [X]/10 | 12% | [X.XX] |
| Traction and Validation | [X]/10 | 12% | [X.XX] |
| **Overall** | | **100%** | **[X.XX]** |

### Dimension Detail

#### 1. Narrative Flow and Story Arc -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 2. Problem/Solution Clarity -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 3. Market Sizing Methodology -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 4. Competitive Positioning -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 5. Financial Projections Realism -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 6. Team Credibility -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 7. Ask Clarity and Use of Funds -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

#### 8. Traction and Validation -- [X]/10

[2-4 paragraphs of detailed analysis with specific references to slides]

---

## Design and Visual Communication Notes

[Bulleted observations about the visual design, layout, and presentation quality]

---

## Top 5 Improvements

These are the five changes that would have the greatest impact on this deck's effectiveness with investors, ranked by impact.

### 1. [Improvement Title]

**Current State:** [What the deck does now]
**Recommended Change:** [Specific, actionable change]
**Expected Impact:** [Why this matters to investors]
**Implementation Difficulty:** Low / Medium / High
**Priority:** Immediate

### 2. [Improvement Title]

[Same structure]

### 3. [Improvement Title]

[Same structure]

### 4. [Improvement Title]

[Same structure]

### 5. [Improvement Title]

[Same structure]

---

## Investor Objection Predictions

### Objection 1: "[Exact phrasing as an investor would say it]"

**Category:** [Market / Execution / Technical / Competitive / Business Model / Timing / Regulatory / Capital Efficiency]
**Severity:** [High / Medium / Low]
**Trigger:** [What in the deck causes this objection]
**Suggested Verbal Response:** [How to handle this in a meeting]
**Deck Fix:** [How to preempt this in the next version]

### Objection 2: "[Exact phrasing]"

[Same structure]

[Continue for all predicted objections, minimum 5]

---

## Comparison to Successful Decks

### Primary Benchmark: [Company Name] ([Round])

**Relevance:** [Why this is the right comparison]

**Where This Deck is Stronger:**
- [Specific comparison point]

**Where This Deck Falls Short:**
- [Specific comparison point]

**Techniques to Borrow:**
- [Specific technique with explanation of how to adapt it]

### Secondary Benchmark: [Company Name] ([Round])

[Same structure]

---

## Missing Slides or Sections

[List any critical slides or content that is entirely absent from the deck but should be present for this stage and industry]

---

## Appendix: Methodology

This review evaluates pitch decks across 8 weighted dimensions on a 1-10 scale. Scores are calibrated against hundreds of funded startup pitch decks. The evaluation focuses on how effectively the deck communicates the investment opportunity to sophisticated venture investors. Design quality is noted but not scored, as it is secondary to content and narrative for most investors.