1. Clarity over sophistication. "80% accurate and 100% clear beats the reverse." If a grandmother can't understand what you do, investors won't either. Eliminate jargon, acronyms, and marketing language.
2. Lead with what's impressive. You earn each additional minute of investor attention. Don't bury traction after 5 sections of problem setup — put the strongest signal right after "what you do."
3. Make investors talk. A pitch isn't a monologue. The more investors talk, the more they convince themselves. Structure the narrative to invite conversation, not shut it down.

• 00-intake/brief.md

  — product description and context

• 01-discovery/market-analysis.md

  — market size, TAM/SAM/SOM

• 01-discovery/competitor-landscape.md

  — competitor profiles

• 01-discovery/target-audience.md

  — customer personas, pain points

• 02-strategy/lean-canvas.md

  — business model summary

• 02-strategy/positioning.md

  — positioning framework

• 05-financial/revenue-model.md

  — revenue projections

• 06-validation/scorecard.md

  — idea scorecard

• competitors-report.md

  — competitive landscape

• battle-cards/

  — per-competitor profiles

• pricing-landscape.md

  — pricing analysis

• positioning-doc.md

  — positioning document

• positioning-statement.md

  — positioning statements, elevator pitch

• competitive-alternatives.md

  — alternatives map

• messaging-implications.md

  — messaging hierarchy

• What does your company do? (2 sentences max — this becomes the opening)
• What problem are you solving and for whom?
• What's your unique insight? (What do you know that others don't?)
• What traction do you have? (users, revenue, growth rate — with timeframes). If none: say so honestly, we'll build the pitch around insight and team instead.
• What's your business model? (one sentence — how do you make money?)
• Who's on the team? (names, roles, key accomplishments — not titles)
• How much are you raising and what will you do with it?

• What's your market size? (or enough data to calculate it)
• Who are your main competitors? What's your advantage?
• What milestones will you hit in 18-24 months with this funding?

• Who is the audience? (VCs, angels, accelerator, demo day, specific fund?)
• What formats do you need? (10-min narrative, 2-min verbal, email pitch, all of them?)

Anti-pattern: "We leverage AI-powered machine learning to optimize cross-functional synergies in the B2B SaaS vertical." Better: "We help sales teams find which leads will actually buy. Our tool analyzes email replies and tells reps exactly who to call next — last month one customer closed 40% more deals."

Reference: Read

references/research-scaling.md

for the complexity scoring matrix, tier definitions, wave configurations, and the user communication template.

1. Score three factors from the intake: market breadth (1-3), known competitors (1-3), geographic scope (1-3)
2. Sum the scores (range 3-9) and map to a tier: Light (3-4), Standard (5-7), Deep (8-9)
3. Present the Research Depth table to the user (see

   research-scaling.md

   for the exact template)
4. Wait for user response: light, deep, or ok to accept the recommendation
5. Record the selected tier in PROGRESS.md

research-scaling.md

Agent

• Agent tool available (Claude Code): Spawn all agents within each wave in parallel. This is faster.
• Agent tool NOT available (Claude.ai, web): Execute research sequentially, following the same templates. Same depth, just slower.

Reference: Read

references/research-principles.md

before starting any wave. It defines source quality tiers, cross-referencing rules, and how to handle data gaps.

Reference: Read

references/research-wave-1-audience-narrative.md

for agent templates.

Reference: Read

references/research-wave-2-competitive-framing.md

for agent templates.

Reference: Read

references/pitch-frameworks.md

for the complete framework, including the integration matrix. Reference: Read

references/research-synthesis.md

for synthesis protocol and output templates.

pitch-frameworks.md

1. Problem — The initial conditions. What's broken? Who suffers?
2. Solution — The experiment. What are you building to fix it?
3. Insight — Why this will work. What non-obvious truth powers this?

1. What You Do — 2 sentences + specific example. Impossible to misunderstand.
2. [Lead with strength] — Whatever is most impressive goes here: traction, team, insight, or market.
3. Traction — Metrics WITH timeframes. "0 to 1,000 users in 8 weeks" not "1,000 users."
4. Unique Insight — What do you know that others don't?
5. Business Model — One clear model. Not a menu of options.
6. Market Size — Bottom-up math. "50,000 customers × $50K ACV = $2.5B" not "$50B TAM."
7. Team — Specific accomplishments, not titles.
8. The Ask — Amount + milestones + timeframe.

• Strong traction? → Lead with traction right after "What You Do"
• Impressive team? → Lead with team credentials
• Breakthrough insight? → Lead with the insight that creates an "aha" moment
• Huge market? → Lead with market opportunity

• No jargon. If the user's pitch contains industry jargon, flag it and provide plain-language alternatives.
• Specific > generic. Replace every vague claim with a specific fact, number, or example.
• Show, don't tell. For the Solution section: describe what a user SEES and DOES — the concrete experience, not abstract features. "The rep opens the dashboard, sees 3 leads highlighted in green with a confidence score. They click one, see the email thread summary, and call. 30 seconds from login to action." This is far more powerful than "Our AI-powered platform surfaces high-intent leads."
• Test the 2-sentence description. If someone hearing it for the first time couldn't explain it back, simplify.

# {Title}: {product}

*Skill: startup-pitch | Generated: {date}*

{project-name}/pitch-full.md

• Opening (2 sentences + example)
• Complete narrative following the ordered elements
• Speaker notes for each section (what to emphasize, where to pause, where to invite conversation)
• Transition sentences between sections
• Closing and ask

{project-name}/pitch-5min.md

• All 8 elements, trimmed to core claim + one supporting proof point
• Speaker notes focused on pacing

{project-name}/pitch-2min.md

• Word-for-word script
• The 2-sentence opener + strongest proof point + insight + ask
• Delivery notes (pace, emphasis, pauses)

{project-name}/pitch-1min.md

• Two versions: formal (investor event) and casual (networking)
• What You Do + Insight + Ask only

{project-name}/pitch-email.md

• Subject line candidates (3 options)
• Email body: hook → what you do → traction/insight → why now → ask → close
• Follow-up email template
• Personalization notes per investor type

{project-name}/pitch-appendix.md

• Top 10 likely investor questions with prepared answers
• Objection handling (competitive threats, market risks, team gaps)
• Known weaknesses with honest answers and mitigation plans
• Financial and competitive backup (if available from prior sessions)

{project-name}/raw/

• investor-audience.md

• comparable-narratives.md

• competitive-framing.md

• why-now-timing.md

Reference: Read

references/verification-agent.md

for the full verification protocol, universal checks, and skill-specific checks.

1. Spawn agent V1: Verification — it reads all deliverable files and checks for: unlabeled claims, internal contradictions, confidence rating consistency, missing data gaps, missing flags, stale data, and duplicate-source false corroboration
2. V1 also runs startup-pitch-specific checks: pitch claims vs. source data, cross-format consistency, pitch vs. appendix alignment, honesty checks (traction without timeframes, top-down TAM, titles without accomplishments)
3. V1 produces

   {project-name}/verification-report.md

4. If Critical issues found: Pause and present issues to the user. Ask: fix first, or proceed as-is?
5. If only Warnings/Info: Show one-line summary and continue to review phase

{project-name}/pitch-scorecard.md

• 65-80: Investor-ready. Go pitch.
• 50-64: Investor-ready with caveats. Address the weak dimensions first.
• 35-49: Needs work. Iterate on the weakest areas before pitching.
• Below 35: Major gaps. Consider running startup-design first to strengthen the foundation.

1. Explain the weakness
2. Ask: "How do we fix this? Do you have more data, or should we reframe?"
3. Iterate on the relevant pitch sections
4. Re-score after changes

• Angel Investor — Technical, focused on founders + idea. Asks "why you?" and probes domain expertise. Friendly but direct.
• Seed VC — Traction-obsessed, looking for product-market fit signals. Asks about metrics, retention, growth rate. Wants to see momentum.
• Series A VC — Scalability + market size obsessed. Asks about unit economics, competitive moats, expansion path. Thinking about the next round already.
• Accelerator Partner — Looking for coachability + speed of execution. Asks about what you've learned, how fast you ship, what you'd do with mentorship.

1. The user delivers their pitch (any format)
2. Stay in character as the chosen investor persona
3. Ask 3-5 questions that this type of investor would ask — drawn from the appendix but adapted to the persona
4. Push back on weak points — investors do this, and the founder needs practice handling it
5. After the Q&A, break character and provide feedback:
   • What landed well
   • Where the investor would have tuned out
   • Which answers were strong vs. unconvincing
   • Specific suggestions for improvement

• The 60-second rule: You earn each additional minute. If the first 60 seconds aren't compelling, the rest doesn't matter.
• Invite conversation. Pause after the insight. If an investor starts talking, let them — they're selling themselves.
• Own the numbers. If asked about a metric, know the exact figure and how you calculated it.
• Handle "I don't know" well. "I don't know, but here's how I'd find out" beats a fabricated answer.
• Practice the 2-sentence opener until it's effortless. This is the single most important part of the pitch.

Reference: Read

references/honesty-protocol.md

for full protocol and anti-pattern details.

1. No inflated metrics. If traction is weak, the pitch should acknowledge it and pivot to insight, team, or speed of execution. Fabricated traction will surface in due diligence and kill the deal.
2. Honest market sizing. Bottom-up math only. Top-down TAM without justification is a red flag to investors — they've seen it thousands of times.
3. Real team credentials. Specific, verifiable accomplishments. "Built X that did Y" — not vague titles or puffed-up bios.
4. Flag pitch weaknesses. Every pitch has gaps. Identifying them proactively (and having a plan to address them) is stronger than pretending they don't exist.
5. Label claims. Use [Data], [Estimate], [Assumption], [Opinion] tags in supporting materials.