Design MVPs for web, mobile, and SaaS applications through adaptive interviews that achieve buildable clarity. Use when a user wants to define, scope, or document an application idea, or when they mention MVP, product requirements, PRD, app idea, or need help turning a concept into something implementable.
/plugin marketplace add Porkbutts/porkbutts-n-taters/plugin install effective-design@porkbutts-n-tatersThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Interview users to extract implementation-ready requirements, then produce a PRD with enough detail to build with minimal ambiguity.
Start here. Get the essential shape of the product.
Exit when: You can explain the app to someone in 30 seconds.
For each role, define concrete scenarios at the feature level.
For each key action, ask:
Probe for edge cases:
Exit when: You could sketch every screen and know what each button does.
Nail down the tech stack. The PRD should specify exactly what to build with.
| Topic | Key questions |
|---|---|
| Frontend | Web app, mobile (React Native, Flutter, native), or both? Which framework (React, Vue, Next.js, etc.)? |
| Backend | BaaS (Supabase, Firebase, Convex)? Custom API (Node, Python, Go)? Serverless functions? |
| Database | Postgres, MongoDB, SQLite? Managed by BaaS or self-hosted? |
| Deployment | Vercel, Netlify, Railway, Fly.io? App stores for mobile? |
| Auth | Built-in (Supabase Auth, Firebase Auth)? Third-party (Auth0, Clerk)? Social providers needed? |
| Integrations | Which external services? What data flows between? |
| Payments | Stripe, RevenueCat? Subscription vs one-time? |
| Notifications | Email (Resend, SendGrid)? Push? What triggers them? |
| Files/Media | Upload types? Size limits? Storage (S3, Supabase Storage, Cloudinary)? |
Exit when: You could set up the project and install dependencies with no ambiguity.
Explicitly define the MVP boundary.
Ask:
Create explicit IN/OUT lists. Push back on scope creep:
Exit when: Clear line between MVP and future work.
Go deeper when:
Move on when:
Phrase questions as:
After the interview, produce this document:
# [Product Name] - MVP PRD
## Overview
[2-3 sentences: what it is, who it's for, core value proposition]
## Roles
| Role | Description | Key Permissions |
|------|-------------|-----------------|
| [Role 1] | [Who they are] | [What they can do] |
## User Scenarios
### [Scenario Name]
**Role:** [Which role]
**Goal:** [What they're trying to accomplish]
**Flow:**
1. [Step with specific UI/action]
2. [Next step]
3. [Outcome]
**Edge Cases:**
- [Edge case]: [How it's handled]
**Acceptance Criteria:**
- [ ] [Specific, testable criterion]
- [ ] [Another criterion]
[Repeat for each scenario]
## Scope
### In Scope (MVP)
- [Feature/capability 1]
- [Feature/capability 2]
### Out of Scope (Future)
- [Deferred feature 1] - [brief reason why deferred]
- [Deferred feature 2]
## Technical Context
### Tech Stack
| Layer | Choice | Notes |
|-------|--------|-------|
| **Frontend** | [Framework - e.g., Next.js, React Native] | [Any specific libraries] |
| **Backend** | [e.g., Supabase, custom Node API] | [Architecture notes] |
| **Database** | [e.g., Postgres via Supabase] | [Key considerations] |
| **Auth** | [e.g., Supabase Auth with Google] | [Providers needed] |
| **Deployment** | [e.g., Vercel, App Store] | [Environments] |
### Integrations
| Service | Purpose | Data Flow |
|---------|---------|-----------|
| [Service] | [Why needed] | [What data, which direction] |
### Key Entities
[Only if helpful - brief description of core data objects and relationships]
### Constraints
- [Any technical constraints, required technologies, etc.]
## Open Questions
- [Any unresolved items that need answers before/during implementation]
START
│
▼
┌─────────────────────────┐
│ Phase 1: Core Concept │ ◄── Always. Get the 30-second pitch.
└──────────┬──────────────┘
│
▼
┌─────────────────────────┐
│ Phase 2: User Scenarios │ ◄── Always. Could you sketch every screen?
└──────────┬──────────────┘
│
▼
┌─────────────────────────┐
│ Phase 3: Technical Ctx │ ◄── Always. Nail down the tech stack.
└──────────┬──────────────┘
│
▼
┌─────────────────────────┐
│ Phase 4: Scope Boundary │ ◄── Always. Clear MVP vs future line.
└──────────┬──────────────┘
│
▼
┌─────────────────────────┐
│ Generate PRD │
└─────────────────────────┘
Ready to produce PRD when ALL are true:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.