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/research-wave-4-distribution.md
View on GitHub# Wave 4: Distribution & Partnerships (2 agents)
Read `research-principles.md` first. Wave 4 agents receive all prior wave findings as context.
---
## Agent D1: Distribution Channel Deep-Dive
```
Research task: Viable distribution channels for {product category} targeting {customer type}
Context: We're designing a startup that {one-sentence description}.
Competitor GTM findings: {summary from Agent B3}
Target audience: {summary from Agent C3}
RESEARCH PROTOCOL:
ROUND 1 — Content & SEO opportunity (3 searches):
- "{product category} keywords" — look for keyword lists, SEO analyses
- Check Ahrefs/Semrush free tools for domain ratings of competitor content
- "{problem} how to" — are there informational queries we could rank for?
Capture: keyword opportunities, content gaps, estimated difficulty.
ROUND 2 — Community & organic (2-3 searches):
- Find the top 5 communities where target customers are active
- Check community rules on self-promotion (some ban it, some welcome it)
- "{product category} referral program" — do competitors use referrals?
ROUND 3 — Paid acquisition benchmarks (2 searches):
- "{industry} Google Ads CPC"
- "{product category} Facebook ads cost per lead"
- "{industry} LinkedIn ads benchmark"
Capture: estimated CPCs, CPLs for relevant channels.
ROUND 4 — Partnership opportunities (2 searches):
- "{product category} integrations marketplace"
- "{adjacent tool} partner program"
OUTPUT FORMAT:
# Distribution Channel Analysis
## Channel Ranking (by expected ROI for a bootstrapped startup)
### Tier 1: High-Impact, Low-Cost
For each channel:
- Channel name
- Why it works for this startup
- Estimated reach
- Estimated CAC
- Time to first results
- How to get started (specific, actionable steps)
### Tier 2: Medium-Impact, Medium-Cost
[Same structure]
### Tier 3: Long-Term Bets
[Same structure]
### Channels to Avoid
- [Channel] — why it won't work for this startup
## SEO / Content Opportunity
- Top 10 keyword opportunities with estimated volume and difficulty
- Content gap analysis: what competitors haven't covered well
- Recommended content strategy (topics, format, frequency)
## Partnership Opportunities
For each potential partnership:
- Partner name/type
- What they get from us
- What we get from them
- How to approach them
- Priority: High / Medium / Low
## First 90 Days Channel Plan
- Week 1-4: [specific actions]
- Week 5-8: [specific actions]
- Week 9-12: [specific actions]
## Data Gaps
- [Channels you couldn't estimate costs for]
Save to: {project-name}/01-discovery/raw/channels.md
```
---
## Agent D2: Geographic & Market Entry Analysis
```
Research task: Geographic and market entry analysis for {product} in {target geography}
Context: We're designing a startup that {one-sentence description}.
Target: {geography / market segment}
RESEARCH PROTOCOL:
ROUND 1 — Geographic market conditions (2-3 searches):
- "{industry} market {target city/country}"
- "{customer type} concentration {geography}"
- "{product category} adoption rate {geography}"
ROUND 2 — Local competitive dynamics (2 searches):
- "{product category} {target geography} startups"
- Local directories / review sites for competitors in target geography
ROUND 3 — Entry barriers (1-2 searches):
- "{industry} barriers to entry {geography}"
- Language, cultural, regulatory, payment differences (for international markets)
OUTPUT FORMAT:
# Geographic & Market Entry Analysis
## Target Market: {geography}
- Market size in this geography: $X
- Customer density: {how concentrated are target customers}
- Competitive intensity: Low / Medium / High
- Regulatory considerations specific to this geography
## Beachhead Market Recommendation
- Recommended first market: {specific city/region/segment}
- Why this market first: {density of target customers, lower competition, founder network, etc.}
- What winning here proves: {validation milestones}
- Expansion path: {market 1} → {market 2} → {market 3}
## Market Entry Risks
- [Risk specific to this geography]
- [Risk specific to this geography]
## Data Gaps
- [Geographic data you couldn't find]
Save to: {project-name}/01-discovery/raw/geographic.md
```
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 |