Skip to content

ferdinandobons/startup-skill / startup-design

startup-design

Verified

Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments. Trigger when the user has a startup idea to explore, wants to validate a business concept, needs a business plan or lean canvas, asks for market sizing or competitive landscape, wants brand positioning or go-to-market strategy, or says anything like "I have an idea for..." or "is this idea worth pursuing". Also handles resuming from a previous checkpoint.

references/output-specs.md

View on GitHub
# Phase Output Specifications

File-by-file requirements for the Strategy, Brand, Product, and Validation phases. Read the section for the phase you're executing — these specs define what each deliverable must contain.

**Contents:** Phase 4 — Strategy · Phase 5 — Brand · Phase 6 — Product · Phase 8 — Validation

---

## Phase 4 — Strategy (`02-strategy/`)

### lean-canvas.md

Build a complete Lean Canvas (1-page business model):
- Problem (top 3)
- Customer Segments
- Unique Value Proposition
- Solution
- Channels
- Revenue Streams
- Cost Structure
- Key Metrics
- Unfair Advantage

### value-proposition.md

- The value proposition canvas (jobs-to-be-done, pains, gains)
- How the product addresses each pain and creates each gain
- The one-sentence value prop
- Proof points and credibility signals

### business-model.md

- Revenue model (how money comes in, pricing tiers)
- Unit economics (CAC, LTV, margins — even rough estimates)
- Scalability considerations
- Dependencies and key partnerships

### positioning.md

Using April Dunford's positioning framework:
- Competitive alternatives (what happens if you don't exist)
- Unique attributes (what you have that alternatives don't)
- Value (what those attributes enable for customers)
- Target market (who cares the most)
- Market category (the context that makes the value obvious)

### go-to-market.md

- Launch strategy (where, how, to whom first)
- First 100 customers plan
- Growth channels ranked by expected impact and cost
- Partnerships and ecosystem plays
- Timeline with milestones

---

## Phase 5 — Brand (`03-brand/`)

### mission-vision-values.md

- **Mission** — Why the company exists (present-tense, action-oriented)
- **Vision** — The world you're building toward (aspirational but credible)
- **Values** — 3-5 core values with brief explanations of what they mean in practice (not generic platitudes — values should help make decisions)

Generate 2-3 options for mission and vision for the user to choose from or remix.

### tone-of-voice.md

- Brand personality traits (3-4 adjectives with definitions)
- Voice principles with "we are / we are not" examples
- Writing samples: how the brand sounds in different contexts (homepage headline, error message, social media post, customer email)
- Vocabulary guide: preferred terms vs. avoided terms

### brand-personality.md

- Brand archetype analysis (which archetype fits and why)
- Emotional attributes
- Visual direction suggestions (not full design, but adjectives and references)
- How the brand should feel compared to competitors

---

## Phase 6 — Product (`04-product/`)

### mvp-definition.md

- Core hypothesis the MVP tests
- Must-have features (the minimum set to test the hypothesis)
- Nice-to-have features (for v1.1, not v1.0)
- Explicitly out of scope (prevent scope creep)
- Success criteria: what results would validate the MVP

### feature-prioritization.md

- Feature list with RICE or MoSCoW prioritization
- Dependencies between features
- Effort estimates (T-shirt sizing: S/M/L/XL)
- Recommended build order

### user-journey.md

- End-to-end user journey map (from discovery to regular usage)
- Key touchpoints and emotions at each stage
- Drop-off risks and mitigation ideas
- The "aha moment" — when does the user first experience value?

---

## Phase 8 — Validation (`06-validation/`)

### validation-playbook.md

- Ordered list of experiments to run, from cheapest/fastest to most expensive
- For each experiment:
  - What assumption it tests
  - How to run it (step-by-step)
  - What to measure
  - What result would validate vs. invalidate the assumption
  - Estimated time and cost
- Examples: landing page test, fake door test, concierge MVP, customer interviews, ad campaign test, wizard of oz, pre-sales
- If customer interviews were deferred in Phase 3.7, they are experiment #1 — no exceptions

Tailor experiments to the specific idea — a B2B SaaS needs different validation than a consumer marketplace.

### risk-analysis.md

- Risk matrix (likelihood × impact) for:
  - Market risks (no demand, timing, regulatory)
  - Product risks (can't build it, won't work)
  - Business risks (can't monetize, can't scale)
  - Team risks (missing skills, founder conflicts)
  - Financial risks (runway, CAC too high)
- For each high-priority risk: mitigation strategy and early warning signals

### assumptions-tracker.md

- Every critical assumption the business plan rests on
- Current confidence level (high/medium/low)
- How to test each assumption
- Status: untested / testing / validated / invalidated

Format as a table for easy scanning and updating.

### experiment-design.md

- Detailed design for the top 3 recommended experiments
- Hypothesis, method, metrics, success criteria, timeline
- Templates the founder can use immediately (interview scripts, survey questions, landing page copy outline)

### kill-criteria.md

Define 5-7 specific, measurable conditions under which the founder should stop or pivot. Tie each to a validation experiment. Be specific: "If fewer than 3/10 interview subjects say they'd pay $X" not "if there's no demand." This protects the founder from sunk-cost thinking.

### scorecard.md

Produce a summary scorecard:

| Dimension | Score (1-10) | Rationale |
|-----------|-------------|-----------|
| Problem severity | | |
| Market size | | |
| Competitive advantage | | |
| Feasibility | | |
| Business model clarity | | |
| Founder-market fit | | |
| Timing | | |
| **Overall** | | |

Be honest. If the idea has weaknesses, say so clearly. The goal is to help the founder make a good decision, not to validate their ego. Include a clear **Verdict** paragraph after the table with an unambiguous recommendation (see the scoring guide in the Radical Honesty Protocol).
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall