Startup Pitch

Startup Pitch

Build investor-ready pitch content in multiple formats. Uses a structured 7-element framework combined with a problem-solution-insight foundation to produce pitch narratives that are clear, compelling, and fundable.

How It Works

INTAKE → RESEARCH (2 sequential waves) → PITCH CONSTRUCTION → REVIEW & PRACTICE

The process: understand the company deeply, research the investor audience and competitive framing, then construct the pitch. Typical runtime: 15-20 minutes in Claude Code (parallel agents), 30-40 minutes in Claude.ai (sequential).

Core Philosophy

Three principles govern every output this skill produces:

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.

Language

Default output language is English. If the user writes in another language or explicitly requests one, use that language for all outputs instead.

Phase 0: Resume Check

Before anything else, check if a PROGRESS.md created by this skill exists in the working directory or a project subdirectory (the skill name field says startup-pitch). If it does, read it and resume from the last incomplete phase. Tell the user: "I found progress from a previous session. You completed [phases]. Picking up from [next phase]."

If no progress file exists — or the one found belongs to a different skill — start from Phase 1.

Phase 1: Intake

Short and focused — 1-2 rounds of questions. The goal is enough context to build a compelling pitch.

Recommended Prior Work

A pitch built on validated data is significantly stronger than one built on self-reported answers. If you haven't already, consider running startup-design first — it provides market research, competitive analysis, business model, financial projections, and a validation scorecard that become the foundation of a much more credible pitch.

Not required. startup-pitch works standalone. But the quality difference is noticeable.

Check for Prior Work

Before asking questions, check if prior sessions have been completed. Look for these files in the working directory or subdirectories:

From startup-design:

• 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

From startup-competitors:

• competitors-report.md — competitive landscape
• battle-cards/ — per-competitor profiles
• pricing-landscape.md — pricing analysis

From startup-positioning:

• positioning-doc.md — positioning document
• positioning-statement.md — positioning statements, elevator pitch
• competitive-alternatives.md — alternatives map
• messaging-implications.md — messaging hierarchy

If these files exist, read them and extract the pitch building blocks: product description, problem/solution, traction, team, market size, business model, positioning, competitive landscape. Tell the user: "I found data from a previous session. I'll use it to build your pitch."

Skip redundant intake questions. Go straight to pitch-specific questions if prior data is sufficient.

What to Ask (if no prior data exists)

Round 1 — The essentials (all required for a pitch):

• 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?

Round 2 — Sharpening (only if needed):

• 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?

Pitch-specific questions:

• 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?)

Don't over-interview. A founder with clear answers to Round 1 has enough to build a strong pitch.

The 2-Sentence Test

Before moving to research, crystallize the company description into exactly 2 sentences + one specific example. This is the foundation of the entire pitch.

Test: send it to a smart friend — could they paraphrase it back correctly? If not, simplify further.

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."

Output

Save to {project-name}/intake.md — consolidated context for pitch construction. Project name: kebab-case (e.g., ai-sales-assistant).

Create {project-name}/PROGRESS.md with: project name, skill name (startup-pitch), start date, language, requested formats, target audience, research mode (Live / Knowledge-Based), and a phase checklist. Update it after each phase completes.

Phase 1.5: Research Depth Assessment

After intake, assess market complexity and present the Research Depth recommendation to the user.

Reference: Read references/research-scaling.md for the complexity scoring matrix, tier definitions, wave configurations, and the user communication template.

Process

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

The selected tier determines the number of agents per wave and search rounds per agent in Phase 2. See research-scaling.md for exact wave configurations per tier.

Phase 2: Research

Two sequential research waves exploring investor audience and competitive/market framing — agents within a wave run in parallel, and Wave 2 builds on Wave 1's findings. Together they provide the raw material for a pitch that resonates with the target audience.

Environment Detection

Check if the Agent tool is available:

• 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.

Web Search

If WebSearch is unavailable, fall back to Knowledge-Based Mode: use training data, mark findings with [Knowledge-Based — verify independently], and reduce confidence ratings by one level. Note the mode in PROGRESS.md.