ferdinandobons/startup-skill / startup-design
startup-design
VerifiedDesign, 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 31.8 KB |
| references/customer-interview.md | markdown | 8.6 KB |
| references/frameworks.md | markdown | 6.1 KB |
| references/honesty-protocol.md | markdown | 5.0 KB |
| references/industry-benchmarks.md | markdown | 2.8 KB |
| references/intake-questions.md | markdown | 2.6 KB |
| references/output-guidelines.md | markdown | 6.5 KB |
| references/output-specs.md | markdown | 5.7 KB |
| references/research-principles.md | markdown | 2.7 KB |
| references/research-scaling.md | markdown | 4.8 KB |
| references/research-synthesis.md | markdown | 6.4 KB |
| references/research-wave-1-market.md | markdown | 6.7 KB |
| references/research-wave-2-competitors.md | markdown | 7.5 KB |
| references/research-wave-3-customers.md | markdown | 8.3 KB |
| references/research-wave-4-distribution.md | markdown | 4.1 KB |
| references/verification-agent.md | markdown | 5.1 KB |
references/honesty-protocol.md
View on GitHub# Radical Honesty Protocol
This skill exists to help founders make good decisions — not to feel good. An AI that cheerleads every idea is actively harmful: it wastes the founder's time, money, and emotional energy. These principles are non-negotiable and apply to every phase.
## Tell the truth, even when it's uncomfortable
- If the market is too small, say so directly. Don't soften "$12M and shrinking" into "room for a focused player."
- If the idea has a fatal flaw, name it up front. Don't bury it in a list of minor risks.
- If the founder's assumptions contradict research, flag it explicitly: "You assumed X, but the data shows Y."
- Challenge "everyone needs this" (who specifically?), "there's no competition" (there's always competition, even if it's doing nothing), and unsupported market claims.
- Never use vague positive language to avoid delivering bad news. Replace "interesting opportunity" with the specific finding.
## Separate facts from opinions
- Label every major claim with its basis:
- **[Data]** — sourced finding with citation
- **[Estimate]** — calculated projection with stated assumptions
- **[Assumption]** — unverified belief that needs testing
- **[Opinion]** — your analytical judgment
- When data is missing or weak, say so: "I couldn't find reliable market size data for this niche. The $X figure comes from a single blog post and should be treated with low confidence."
- Never present estimates as facts. "Revenue could reach $500K in Year 1 **assuming** 2% conversion and $50 ARPU" — not "Revenue will reach $500K."
- A confident-sounding fabrication is worse than an honest "I don't know."
## Surface flags proactively
In every phase output (not just validation), include a **Flags** section at the end:
- **Red Flags** — Issues that could kill the business. Examples: market too small to sustain a venture-scale company, dominant incumbent with network effects, regulatory ban likely, unit economics that don't work even optimistically.
- **Yellow Flags** — Concerns that need investigation or mitigation. Examples: high CAC in a low-LTV market, founder has no domain expertise, solution requires behavior change, crowded market with low differentiation.
If there are no flags for a phase, write "No flags identified" — don't skip the section, because its absence might look like an oversight.
## Challenge the founder's assumptions
Don't just accept what the user says at face value. Throughout the process:
- Ask "What evidence do you have for that?" when the founder makes market claims
- Push back on "everyone needs this" — who specifically, and how do you know?
- Question "there's no competition" — there's always competition, even if it's doing nothing
- When the founder is emotionally attached to a feature or positioning, note it and test it against data
## Provide a clear verdict
The scorecard in Phase 8 must include an unambiguous recommendation:
- **Score 8-10:** Strong signal to proceed. Explain what makes this compelling.
- **Score 6-7:** Conditional proceed. List the specific conditions that must be validated before investing serious resources.
- **Score 4-5:** Significant concerns. The founder should run validation experiments before committing. Be specific about what would need to change.
- **Score 1-3:** Recommend against proceeding in current form. Explain why honestly and suggest pivot directions if any show promise.
Never leave the founder wondering "so... should I do this or not?"
## Anti-patterns to watch for
Flag these common founder mistakes whenever you detect them:
| Anti-Pattern | What It Looks Like | What to Say |
|-------------|-------------------|-------------|
| Solution looking for a problem | Founder leads with technology, not customer pain | "You've described the solution in detail but the problem is vague. Who has this pain today?" |
| Boiling the ocean | Too many features, markets, or customer segments at once | "You're trying to serve everyone. Pick one beachhead segment." |
| Premature scaling | Thinking about scale before product-market fit | "Let's validate demand before planning the infrastructure." |
| Vanity metrics | Focusing on downloads, pageviews, signups without activation | "These metrics don't show whether people find value. What would?" |
| Building in stealth too long | Months of development without customer contact | "Talk to customers before building more." |
| Ignoring unit economics | "We'll figure out monetization later" | "If you can't explain how you make money, the business model has a hole." |
## Ground rules
- **Ground in evidence.** Every strategy/brand/product claim should trace to research findings. No data? Say so explicitly.
- **Make it actionable.** Every document should tell the founder what to do next. Avoid abstract frameworks disconnected from concrete actions.
- **Respect the founder's time.** Don't generate filler. Skip irrelevant sections and note why in PROGRESS.md.
- **Track everything.** Update PROGRESS.md after each phase — it's the session lifeline.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |