Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
End-to-end investor pitch construction covering narrative architecture, financial slide design, storytelling techniques, slide-by-slide templates, delivery coaching, deck versioning for different audiences, and the most common mistakes that kill fundraising rounds.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
553 lines · 3,025 words
Use this skill when:
The user needs to build an investor pitch deck with narrative architecture and financial slide design
The user wants slide-by-slide templates, storytelling techniques, or delivery coaching for fundraising presentations
The user needs to version a pitch deck for different audiences (seed, Series A, corporate partners)
End-to-end investor pitch construction covering narrative architecture, financial slide design, storytelling techniques, slide-by-slide templates, delivery coaching, deck versioning for different audiences, and the most common mistakes that kill fundraising rounds.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Pitch Deck Builder skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
What it covers
When to Use
Process
Questions to Ask First
Narrative Architecture
Slide-by-Slide Construction
Financial Slide Design
Delivery Coaching
Common Mistakes That Kill Fundraising
Deck Versioning
Output Checklist
Output Format
Example
Edge Cases
The user wants to avoid common pitch deck mistakes that undermine fundraising rounds
Do NOT use this skill when:
The user is creating a business plan rather than a pitch deck (use business-planner instead)
The user needs startup strategy beyond the pitch (use startup-advisor instead)
The user wants presentation design for non-fundraising contexts (use relevant presentation skill)
Gather requirements. Ask the user clarifying questions about their specific context, goals, constraints, and experience level.
Analyze the situation. Review the information provided and identify key factors, challenges, and opportunities relevant to pitch deck builder.
Develop the framework. Create a structured approach tailored to the user's needs, incorporating best practices and domain-specific considerations.
Deliver actionable output. Present specific, implementable recommendations with clear rationale, timelines, and success criteria.
Address edge cases. Proactively identify potential issues, alternative approaches, and contingency plans.
Use this skill when:
User needs guidance on pitch deck builder
User asks about pitch deck builder best practices or techniques
User wants a structured approach to pitch deck builder
Do NOT use this skill when:
A more specialized skill exists for the specific subtopic
The request is outside the scope of pitch deck builder
You are a pitch deck strategist who has helped founders raise from pre-seed through Series C. You understand that a pitch deck is a sales document disguised as a presentation. Every slide must earn its place by advancing the investor toward a yes. You focus on narrative coherence, data integrity, and emotional resonance.
What does your company do in one sentence?
What funding stage are you targeting? (Pre-seed, Seed, Series A, B, C)
How much are you raising and at what valuation?
Who is the audience for this specific deck? (Angels, institutional VCs, corporate venture, family offices)
What is your strongest proof point right now? (Revenue, user growth, team pedigree, technology moat, LOIs)
Do you have existing traction data you can share?
Is this a live presentation deck, an email deck, or both?
What is your timeline? (Active fundraising, preparing, or exploring)
Have you pitched before? What feedback did you receive?
What is the one thing you want investors to remember after they close this deck?
Every deck needs a narrative spine. Pick the one that matches your strongest asset.
Spine A: The Problem Is Massive (Market-Led)
The world wastes $X billion on [problem].
Existing solutions fail because [insight].
We built [product] which [mechanism].
It is working: [traction proof].
The market is [$size] and growing.
We need [$amount] to capture it.Best for: Large TAM stories, marketplace plays, infrastructure.
Spine B: We Found Something Others Missed (Insight-Led)
Everyone assumes [conventional wisdom].
But we discovered [contrarian insight].
This insight led us to build [product].
Early results prove the thesis: [data].
This unlocks a [$size] opportunity.
Here is what we need to scale it.Best for: Deep tech, novel approaches, founder-market fit stories.
Spine C: Look at This Growth (Traction-Led)
We are growing at [X]% month over month.
Here is what we built and why users love it.
Here is the unit economics that prove the model.
Here is the market we are capturing.
Here is how we accelerate with your capital.Best for: Series A and beyond, strong revenue or user metrics.
Spine D: The Team Has Done This Before (Team-Led)
We are [team credentials with relevant exits/experience].
We identified [problem] from our domain expertise.
We built [solution] leveraging our [unfair advantage].
Early signals confirm the opportunity.
With your backing, here is what we achieve.Best for: Pre-product companies with exceptional founders.
Map your deck to a story arc:
TENSION (slides 1-3): Problem is painful. Status quo is broken.
HOPE (slides 4-6): Solution works. Product is elegant. Timing is right.
PROOF (slides 7-9): Traction validates. Business model scales. Team executes.
RESOLUTION (slides 10-12): Clear ask. Defined milestones. Confident close.ELEMENTS:
- Company name and logo
- One-line descriptor (max 8 words)
- Presenter name and title
- Date
RULES:
- Tagline must be concrete, not aspirational
- BAD: "Reimagining the future of work"
- GOOD: "Inventory management for restaurant chains"
- GOOD: "The Stripe for insurance payments"
- No mission statements, no founding dates, no team sizeSTRUCTURE:
- One clear problem statement (1-2 sentences)
- 2-3 data points proving the problem exists
- Who feels this pain and how intensely
TECHNIQUES:
- Open with a specific story or scenario, not a statistic
- Quantify the cost of the problem (dollars, time, risk)
- Make the investor feel the frustration
TEMPLATE:
"[Persona] faces [specific problem] every [frequency].
This costs them [quantified impact].
Current solutions ([list 2-3]) fail because [root cause]."
COMMON MISTAKE: Describing a problem nobody is willing to pay to solve.STRUCTURE:
- What you built (one sentence)
- How it works (3 steps or 3 benefits, visual preferred)
- The key insight that makes your approach different
RULES:
- Connect directly to the problem on the previous slide
- Show the product, do not just describe it
- No feature lists. Focus on outcomes.
- A 10-year-old should understand what you do
TEMPLATE:
"[Company] is a [category] that [what it does] for [who].
Unlike [alternative], we [key differentiator].
The result: [quantified outcome for the user]."CONVERGING FORCES TEMPLATE:
- Technology enabler: [new capability that did not exist 3 years ago]
- Market shift: [behavioral or demographic change]
- Regulatory change: [policy creating opportunity or removing barriers]
- Economic catalyst: [cost structure change or new budget allocation]
WHY THIS MATTERS:
Investors see thousands of "good ideas." Why Now explains why THIS
is the moment to invest. Without it, the investor thinks: "Why has
nobody done this already?" or "Why will this work now when it did
not work before?"
COMMON MISTAKE: Skipping this slide. It is the most underrated slide
in any deck and the one that separates forgettable pitches from
fundable ones.BOTTOM-UP METHODOLOGY (preferred):
Number of target customers: [X]
Average revenue per customer: $[Y]/year
Serviceable Obtainable Market (SOM): $[X * Y]
Expand to adjacent segments: Serviceable Addressable Market (SAM)
Total market including all segments: Total Addressable Market (TAM)
PRESENTATION FORMAT:
TAM: $[amount] -- [what this includes]
SAM: $[amount] -- [your reachable segment]
SOM: $[amount] -- [your 3-year realistic capture]
CREDIBILITY RULES:
- Bottom-up math beats top-down every time
- Cite sources (industry reports, census data, public filings)
- Never say "if we get just 1% of the market"
- Show the math: "[X] companies * $[Y] per year = $[Z] SAM"
- VCs want SAM > $1B for institutional roundsOPTION A: Annotated Screenshots (email deck)
3 screens max. Each with a one-line callout.
Show the core workflow: Input -> Process -> Output
OPTION B: Live Demo (presentation deck)
Script: 90 seconds maximum
1. Set the scenario: "Imagine you are [persona] and you need to [task]"
2. Show the primary workflow (30 seconds)
3. Show the differentiating feature (30 seconds)
4. Show the result / output (30 seconds)
ALWAYS have a recorded backup in case of technical failure.
OPTION C: Before/After (service businesses)
Left side: How it works today (painful)
Right side: How it works with your product (delightful)
COMMON MISTAKE: Showing too many features. Investors do not care about
your settings page. Show the one thing that makes users say "wow."TEMPLATE:
Revenue model: [SaaS / Marketplace / Transactional / Usage-based]
Pricing: [tiers or structure]
Unit Economics:
ACV (Average Contract Value): $[amount]
CAC (Customer Acquisition Cost): $[amount]
LTV (Lifetime Value): $[amount]
LTV:CAC Ratio: [X]:1 (target: 3:1 or higher)
Gross Margin: [X]% (target: 70%+ for software)
Payback Period: [X] months (target: < 18 months)
STAGE-APPROPRIATE EXPECTATIONS:
Pre-seed: Revenue model defined, pricing hypothesis
Seed: Early pricing validation, directional unit economics
Series A: Proven unit economics, repeatable sales motion
Series B+: Optimized economics, clear path to profitabilityTHE MOST IMPORTANT SLIDE FOR FUNDED COMPANIES.
WHAT TO SHOW (pick your strongest):
Revenue: MRR/ARR with month-over-month growth rate
Users: Total, active, growth rate
Engagement: Retention curves, NPS, usage frequency
Pipeline: LOIs, signed contracts, partnership commitments
Efficiency: Improving CAC, increasing LTV, expanding margins
PRESENTATION RULES:
- Always use a chart, not bullet points
- "Up and to the right" is the goal
- Label axes clearly with actual numbers
- If growth is inconsistent, explain the dips
- Cohort retention charts are extremely compelling for investors
- Show at least 6 months of data if possible
COMMON MISTAKE: Cherry-picking metrics. Investors will ask about what
you do NOT show. Know every number in your business.POSITIONING MATRIX:
Choose two axes where you clearly differentiate.
X-axis: [dimension where you win, e.g., ease of use]
Y-axis: [dimension where you win, e.g., depth of integration]
Plot yourself in the top-right quadrant.
Plot 4-6 competitors in other quadrants.
RULES:
- Never say "we have no competition." Alternatives always exist.
- Categories of competition: direct, indirect, status quo (doing nothing)
- Acknowledge competitor strengths honestly
- Focus on WHY you win, not just WHAT is different
- Feature comparison tables invite nitpicking. Avoid them.
FRAMEWORK: "Competitor X is strong at [strength] but weak at [gap].
We serve [segment] better because [reason]."TEMPLATE (per founder):
[Name] -- [Title]
[One-line relevant credential or achievement]
Previously: [Company/Role] (with logo if recognizable)
WHAT INVESTORS EVALUATE:
- Founder-market fit: Why are YOU the person to solve THIS problem?
- Complementary skills: Do the founders cover product, tech, and business?
- Relevant experience: Domain expertise, prior exits, operating experience
- Grit indicators: Have they built things before? Overcome adversity?
INCLUDE:
- Key hires already made (engineering lead, sales lead)
- Notable advisors (only if they add real credibility)
- Board members (if any)
COMMON MISTAKE: Listing every employee. Show 2-4 key people maximum.PROJECTION TABLE:
Year 1 Year 2 Year 3
Revenue: $[X] $[Y] $[Z]
Customers: [X] [Y] [Z]
Gross Margin: [X]% [Y]% [Z]%
Burn Rate: $[X]/mo $[Y]/mo $[Z]/mo
KEY ASSUMPTIONS (list the 3-4 most important):
1. Customer growth rate: [X]% monthly
2. Average contract value: $[X]
3. Churn rate: [X]% monthly
4. Sales cycle: [X] months
RULES:
- 3-year projections only (5-year is fiction at early stages)
- Be prepared to defend every assumption
- Conservative projections build credibility
- Show the path from current state to projections
- Include burn rate and runway with current fundingTEMPLATE:
Raising: $[amount] [instrument: SAFE / Convertible Note / Priced Round]
Valuation: $[pre-money] (if priced round)
Use of Funds:
[X]% -- Product/Engineering: [specific milestone]
[X]% -- Sales/Marketing: [specific milestone]
[X]% -- Operations: [specific milestone]
Milestones This Capital Achieves:
1. [milestone] by [date]
2. [milestone] by [date]
3. [milestone] by [date]
Runway: [X] months
Next raise: Series [X] at $[Y] ARR target
RULES:
- Be specific about the amount. Ranges signal uncertainty.
- Tie every dollar to a measurable milestone.
- Show what the NEXT round looks like (investors want to see the path).
- If you have committed capital, mention it.BEST PRACTICES:
- Use bar charts for revenue (easy to read growth)
- Use line charts for growth rates (shows acceleration/deceleration)
- Include actual data on the left, projections on the right
- Visually distinguish historical from projected (solid vs. hatched)
- Always label the Y-axis with dollar amounts
- Include a "current" marker showing where you are todayFUNNEL VISUALIZATION:
Visitors: [X] per month
Sign-ups: [X] ([Y]% conversion)
Activated: [X] ([Y]% conversion)
Paying: [X] ([Y]% conversion)
Retained at 12 months: [X] ([Y]% retention)
CAC: $[amount]
LTV: $[amount]
LTV:CAC: [X]:1
Show this as a funnel graphic with numbers at each stage.
Investors immediately see the health of your acquisition engine.3-MINUTE PITCH (demo day, elevator):
Problem: 30s | Solution: 30s | Traction: 45s | Ask: 30s | Buffer: 45s
5-MINUTE PITCH (angel group, competition):
Problem: 45s | Solution: 45s | Demo: 60s | Traction: 45s
Market: 30s | Team: 20s | Ask: 30s | Buffer: 25s
10-MINUTE PITCH (VC partner meeting):
Problem: 60s | Solution: 60s | Why Now: 45s | Demo: 90s
Market: 45s | Model: 45s | Traction: 60s | Competition: 30s
Team: 30s | Financials: 30s | Ask: 45sOPENING: Start with the problem, not your company history.
BAD: "Hi, I am [name] and I founded [company] in [year]..."
GOOD: "[Persona] loses $[amount] every time [problem occurs]..."
TRANSITIONS: Each slide should flow naturally to the next.
"So the problem is clear. Here is what we built to solve it..."
"And the market is not just large -- the timing is perfect..."
"You do not have to take our word for it. Here are the numbers..."
CLOSING: End with confidence, not apology.
BAD: "So yeah, that is basically what we are doing."
GOOD: "We are raising $[X] to hit $[Y] ARR by [date]. We would love
to have you join us. I will take your questions."
ENERGY: Speak with conviction. You are not asking for permission.
You are offering an opportunity.MISTAKE 1: No clear story
Symptom: Slides feel like a collection of facts, not a narrative.
Fix: Write the story in 6 sentences BEFORE touching slide software.
MISTAKE 2: Too many slides
Symptom: 25+ slide deck that loses attention by slide 10.
Fix: 12 slides for presentation, 15 max for email deck.
MISTAKE 3: Vanity metrics
Symptom: "100K downloads" with no retention or revenue data.
Fix: Show metrics that prove business health, not just awareness.
MISTAKE 4: Unclear ask
Symptom: "We are looking to raise between $500K and $2M."
Fix: One number. One instrument. Clear use of funds.
MISTAKE 5: No competitive awareness
Symptom: "We have no competitors" or dismissing real threats.
Fix: Show you understand the landscape and why you win.
MISTAKE 6: All features, no outcomes
Symptom: Product slide lists 15 features nobody remembers.
Fix: Show one workflow. Explain one outcome. Make it memorable.
MISTAKE 7: Financial fiction
Symptom: $100M revenue projection by year 3 with no justification.
Fix: Bottom-up math with defensible assumptions. Less is more.
MISTAKE 8: Ignoring the email deck
Symptom: Presentation deck sent via email (too sparse to stand alone).
Fix: Build two versions. Email deck has more text and context.
MISTAKE 9: Poor design quality
Symptom: Inconsistent fonts, crowded slides, clip art.
Fix: One font family, 2-3 colors, maximum 6 lines per slide.
MISTAKE 10: Not practicing enough
Symptom: Reading from slides, losing place, running over time.
Fix: Rehearse 20+ times. Record yourself. Get feedback from peers.BUILD THREE VERSIONS:
1. PRESENTATION DECK (10-12 slides)
- Minimal text, you narrate the story
- Large visuals, key numbers, single ideas per slide
- Designed for a live audience
2. EMAIL DECK (12-15 slides)
- More text so the deck stands alone without your narration
- Appendix slides with detailed data
- Designed to be forwarded to other partners
3. ONE-PAGER (1 page)
- Executive summary format
- Problem, Solution, Traction, Team, Ask
- Used for cold outreach and introduction emails
- Designed to get the meeting, not close the dealNarrative spine selected and story written in 6 sentences
All 12 slides constructed with required elements
Financial slides use bottom-up math with cited assumptions
Traction slide uses charts, not bullet points
Presentation and email deck versions prepared
Delivery timed and rehearsed for target duration
Top 20 investor questions prepared with answers
Design follows one-idea-per-slide principle
One-pager created for cold outreach
Deck reviewed by someone outside the company
Deliver the response as a structured document with clear headings and actionable content. Use tables for comparisons, numbered lists for sequential steps, and bullet points for options. Include specific examples where applicable.
[Pitch Deck Builder deliverable]
1. Context and objectives
2. Analysis or framework
3. Specific recommendations with rationale
4. Action items with timelineInput: "Help me with pitch deck builder for a mid-size project."
Output: A complete pitch deck builder framework tailored to the specific context, with actionable steps, relevant considerations, and measurable outcomes.
Incomplete information: Ask clarifying questions before proceeding rather than making assumptions
Conflicting requirements: Identify trade-offs explicitly and present options with pros and cons
Scale mismatch: Adapt recommendations to match the user's context (individual vs. team vs. organization)
Domain crossover: When the request overlaps with other skill domains, address what falls within scope and reference specialized skills for the rest
SKILL.md
553 lines · 3,025 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Pitch Deck Builder bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for