prototype
Guides a new idea from vague concept to working MVP — scoping, stack choice, architecture, implementation, and deployment in one structured workflow. Make sure to use this skill whenever the user says "new project", "start a project", "build an MVP", "side project idea", "I want to build X", "prototype this", "launch something", or invokes /prototype. Also use proactively when someone describes a new idea they want to build, even if they don't explicitly ask for a prototype workflow.
What this skill does
# Prototype Workflow Structured path from idea → working MVP. Most side projects die in "where do I even start" — this is the scaffolding. Discard it once momentum exists. ## Phase 0 — Scope Calibration Ask first. The answer changes everything. > "Is this a quick side project or something you want to take seriously?" - **Side project / weekend hack**: skip formality, move fast, Phase 3 is a one-liner, deployment is optional for now - **Serious startup / real product**: run all phases with full depth ## Phase 1 — Clarify the Idea 3 questions max. Don't proceed until all 3 have clear answers. 1. **Who is this for?** (specific person/role, not "everyone") 2. **What's the one thing it does?** (if you need "and", it's two products) 3. **What does "done" look like for v1?** (the minimum that a real user could actually use) If the user can't answer #2 without "and", help them cut. ## Phase 2 — Tech Stack Recommend based on project type and stated skills. Offer 2 options with honest trade-offs — don't just list everything. **Web app (default for solo dev speed):** - Next.js + Vercel — fastest from zero to deployed, great DX, edge-ready - SvelteKit + Vercel — smaller bundle, less ecosystem, better if React fatigue **API / backend:** - Hono + Bun — fast, minimal, TypeScript-first, great for side projects - FastAPI — Python, better if the user has ML or data science adjacent work **Mobile:** - Expo (React Native) — ship to iOS + Android from one codebase, Vercel-style DX for mobile **CLI:** - Node.js + commander — if the user knows JS - Python + click or Typer — if the user knows Python **Database (don't overcomplicate v1):** - Turso (libSQL) or Neon (Postgres) + Drizzle ORM — serverless, free tier - Supabase — if auth + realtime + storage are needed out of the box State the trade-off plainly: "Next.js is the default because it ships fastest. Use SvelteKit if bundle size is a constraint or you dislike React's mental model." ## Phase 3 — Architecture One-paragraph overview only. No architecture astronautics. Cover: - Data model (3–5 entities max for v1) - Key routes or components - Auth approach (no auth / magic link / OAuth — pick based on audience) If the user is over-engineering, say so: "You don't need a message queue for an MVP with 10 users." ## Phase 4 — Implementation Use the Task tool to spawn a coder subagent with full context: - Stack decision + rationale - Data model - V1 scope (the "done" definition from Phase 1) Set up in order: repo → CI if needed → core feature → README. ## Phase 5 — Ship Checklist Before declaring done: - [ ] Env vars not committed (`.env` in `.gitignore`) - [ ] Domain configured (or Vercel preview URL is fine for MVP) - [ ] Basic error monitoring (Sentry free tier — 5 min setup) - [ ] Rate limiting on public endpoints (Upstash is free + easy) - [ ] Analytics if you need user data (Vercel Analytics or Plausible) - [ ] README with one-liner description and setup instructions Skip items that don't apply to a side project — the checklist is a prompt, not a requirement.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.