startup-design

What this skill does

# Startup Design

A structured, multi-phase skill that takes a startup idea from raw concept to validated design. It produces a complete set of markdown documents organized by domain, with built-in progress tracking so work survives session interruptions.

## How It Works

The process has 8 phases executed sequentially. Each phase produces output files and updates the progress tracker. If a session is interrupted, resume from the last completed checkpoint.

```
INTAKE → BRAINSTORM → RESEARCH → STRATEGY → BRAND → PRODUCT → FINANCIAL → VALIDATION
```

### Modes

**Full Mode (default):** Execute all 8 phases in order. Best for thoroughly designing a startup from scratch.

**Fast Track Mode:** When the user says they want a "quick validation," "rapid assessment," or similar, or when time/budget is clearly limited, run a compressed version:
1. Phase 1 (Intake) — shortened to 1 round of questions
2. Phase 2 (Brainstorm) — 3 variations instead of 5-8
3. Phase 3 (Research) — Wave 1 + Wave 2 only (skip customer voice and distribution deep-dives)
4. Phase 4 (Strategy) — Lean Canvas only
5. Skip Phase 5 (Brand) and Phase 6 (Product)
6. Phase 7 (Financial) — Revenue model only, no full projections
7. Phase 8 (Validation) — Scorecard + top 3 experiments only

Fast Track produces fewer files but still gives the founder a clear go/no-go signal with evidence. Note in PROGRESS.md that Fast Track mode was used, so a future session can expand to full mode if the idea passes validation.

### Language

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

---

> **Reference:** Read `references/output-guidelines.md` once at the start. It defines the standard file header/footer (title, date, phase, confidence, flags), cross-phase referencing format, quality examples of good vs. bad output, and how to handle mid-process pivots.

## Phase 0: Resume Check

Before anything else, check if a `PROGRESS.md` file exists in the working directory (or a project subdirectory). 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, start from Phase 1.

---

## Phase 1: Intake Interview

The quality of everything downstream depends on how much context you extract now. Don't rush this — a thorough intake saves hours of misdirection later.

### Core Questions

Ask these in a conversational flow, not as a rigid checklist. Group related questions naturally and adapt based on answers. Not every question applies to every startup — skip what's irrelevant.

**The Idea**
- What problem are you solving? Who has this problem?
- What's your proposed solution? How does it work?
- What triggered this idea? (personal pain, market observation, technical insight)
- Do you have any existing work? (prototypes, research, landing pages, waitlists)

**The Founder(s)**
- What's your background? Relevant domain expertise?
- Are you solo or do you have co-founders? What are their strengths?
- How much time can you dedicate? Full-time or side project?
- What's your budget/runway situation?

**The Market**
- Who is your ideal customer? Be as specific as possible.
- How do they currently solve this problem? (existing alternatives, workarounds)
- Do you know of direct competitors? Who are they?
- What geography/market are you targeting first?

**The Business**
- How do you plan to make money? (subscription, one-time, marketplace, freemium)
- Any idea of pricing?
- What does success look like in 6 months? 12 months? 3 years?
- What are your biggest unknowns or worries?

**Constraints & Preferences**
- Any technical constraints? (must be mobile-first, needs to integrate with X)
- Any strong opinions on brand/positioning? (premium vs accessible, playful vs serious)
- Regulatory considerations?

### Hard Questions

After the core questions, ask these deliberately uncomfortable questions. They surface blind spots early:
- "Why are you the right person to build this? What unfair advantage do you have?"
- "If Google/a well-funded competitor launched this tomorrow, what would you do?"
- "What's the strongest argument against this idea?"
- "Have you talked to potential customers? What did they actually say (not what you hoped they'd say)?"
- "What would make you walk away from this idea?"

Don't skip these — they set the tone for the entire process and signal that this is an honest assessment, not a cheerleading session.

### How to Interview

- Ask 3-5 questions at a time, not all at once
- Acknowledge and build on answers — show you're listening
- Probe vague answers: "You said 'small businesses' — can you narrow that down? Like, freelancers? 10-person agencies? Local retail?"
- After 2-3 rounds, summarize what you've understood and ask the user to confirm or correct

### Output

Save the consolidated intake to `{project-name}/00-intake/brief.md` with all captured information organized clearly. The project name should be derived from the startup idea (kebab-case, e.g., `pet-health-tracker`).

Create `PROGRESS.md` at the project root with: project name, start date, language, a checklist of all 8 phases (mark Phase 1 complete), and a Notes section for session state.

---

## Phase 2: Brainstorm

Before diving into research, explore the idea space. This prevents premature convergence on the first version of the idea.

### Process

1. **Diverge** — Generate 5-8 variations of the core idea. Push boundaries:
   - What if the target market was completely different?
   - What if the business model was inverted?
   - What if you solved a smaller/larger version of the problem?
   - What adjacent problems could you solve instead?
   - What would the "10x version" look like vs. the "simplest possible version"?

2. **Analyze** — For each variation, note:
   - What's exciting about it
   - What's risky or hard
   - How it changes the competitive landscape

3. **Converge** — Present the variations to the user. Help them identify which elements resonate. The goal isn't to pick one variation — it's to enrich the original idea with insights from the exploration.

4. **Refine** — Based on the user's reactions, crystallize the refined idea. Update the brief if the idea evolved significantly.

### Output

Save to `{project-name}/00-intake/brainstorm.md`. Update PROGRESS.md.

---

## Phase 2.5: Research Depth Assessment

After intake (and brainstorm if applicable), 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 3. See `research-scaling.md` for exact wave configurations per tier.

---

## Phase 3: Market Research

This is the most resource-intensive phase. It uses 4 sequential waves of web research, each building on the previous one's findings.

### Environment Detection

Check if the `Agent` tool is available (Claude Code) or not (Claude.ai, other environments):

- **Agent tool available:** Spawn subagents in parallel within each wave, as described below. This is faster (~3-5 min per wave).
- **Agent tool NOT available (Claude.ai, web):** Execute the research yourself, sequentially. For each wave, follow the same agent templates from the reference files, but run the sear