mvp-architect
from shipshitdev/library
Claude, Cursor, Codex skills and commands
npx skills add https://github.com/shipshitdev/library --skill mvp-architectSKILL.md
MVP Architect - Minimum Viable Product Scoping
Overview
Help indie founders scope the smallest possible product that validates their core hypothesis using Hexa's methodology. Get to market in 3 months or less.
Hexa's Core Principle: "Launch an MVP with key high-value features within 3 months. It's better to launch with clear, easily understood features, even if they aren't at full power yet."
When This Activates
- "What should my MVP include"
- "Help me scope my MVP"
- "What features do I need"
- "What to build first"
- "Been building for months, haven't launched"
Hexa's 7 Principles
- Dig Beyond User Requests — Root needs, not surface wants
- Combat Confirmation Bias — Challenge assumptions
- Partner with Design Partners Early — Build with real users
- Prioritize Adaptable Milestones — 6-month goals, 2-week sprints
- Sketch Before Designing — Keep ugly until validated
- Build Around Dry Elements — Only include stable features
- Stress-Test Architecture — Database design affects everything
Quick Workflow
Step 1: Problem Clarity Check
- 10+ customer interviews?
- One-sentence problem?
- 3-5 design partners?
Step 2: Core Hypothesis
We believe that [customer] has a problem with [pain point].
We believe that [solution] will solve this.
We will know we're right when [success metric].
Step 3: Feature Prioritization
For each feature ask:
- Tests core hypothesis? → Keep
- Users explicitly asked? → Maybe
- Critical path? → Keep
- Can do manually? → Don't build
Target: 3-5 features maximum.
Step 4: Dry Elements Test
Only build features that remained stable through ALL design partner feedback.
Step 5: User Journey (3-4 Screens)
- How do users sign up?
- First action?
- Core value delivery?
- Success confirmation?
Anti-Scope Creep Checklist
Before adding ANY feature:
- Does this test our core hypothesis? → If no, cut it
- Have 3+ design partners asked? → If no, defer it
- Can we launch without this? → If yes, defer it
- Can we do this manually first? → If yes, don't build it
- Will this delay launch by >3 days? → If yes, cut it
The "Launch in 2 Weeks" Test
If you HAD to launch in 2 weeks, what would you cut? Whatever you'd cut... cut it now. That's your real MVP.
Integration
idea-validator- Validate before scopingstartup-icp-definer- Define who you're building forfullstack-workspace-init- Set up codebasebrand-architect- Name and position product
For complete hypothesis framework, feature prioritization matrix, dry elements identification, screen mapping, technical architecture checklist, timeline templates, and output format, see: references/full-guide.md