v0-dev
Generate UI components with v0.dev, the AI-powered UI generator by Vercel. Use when a user asks to prototype React components, generate shadcn/ui layouts, create landing pages, or scaffold UI from natural language prompts.
What this skill does
# v0 — AI-Powered UI Generation ## Overview You are an expert in v0 by Vercel, the AI tool that generates React components and full-page UIs from natural language descriptions. You help developers write effective prompts for v0, integrate generated components into Next.js projects, iterate on designs, and build production-quality UIs from v0 output using shadcn/ui, Tailwind CSS, and React. ## Instructions ### Effective Prompts ```markdown ## What Makes a Good v0 Prompt ### ✅ Good: Specific, visual, with data examples "A pricing page with 3 tiers: Starter ($9/mo — 5 projects, 1 user), Pro ($29/mo — unlimited projects, 5 users, priority support, MOST POPULAR badge), Enterprise (custom pricing — SSO, audit logs, dedicated support, 'Contact Sales' button). Each tier is a card with a feature checklist. Use shadcn/ui, make the Pro tier visually prominent with a border and badge." ### ❌ Bad: Vague, no visual details "Make me a pricing page" ## Prompt Patterns That Work ### 1. Dashboard with real data "An analytics dashboard showing: DAU chart (line, last 30 days, current 12.4K), revenue chart (bar, monthly, $45K this month), conversion funnel (signup→trial→paid, percentages), and a table of top 10 pages by traffic. Dark theme, minimal." ### 2. Form with validation states "A multi-step checkout form: Step 1 — shipping address (name, address, city, state, zip with autocomplete). Step 2 — payment (card number, expiry, CVV with Stripe-style formatting). Step 3 — review order with item list and totals. Show a progress bar at top. Include error states and loading states." ### 3. Data table with actions "A user management table with columns: name (with avatar), email, role (admin/member/viewer as colored badge), status (active/suspended), last login (relative time). Include: search bar, role filter dropdown, bulk select checkboxes, and a row action menu (edit/suspend/delete). Pagination at bottom." ``` ### Integration Workflow ```bash # v0 generates shadcn/ui components — they drop right into Next.js projects # 1. Set up your project with shadcn npx create-next-app@latest my-app --typescript --tailwind --app cd my-app npx shadcn@latest init # 2. Install components v0 uses npx shadcn@latest add card table badge button input select avatar npx shadcn@latest add sheet dialog dropdown-menu tabs # 3. Copy v0 output into your project # v0 provides "Add to Codebase" button that generates npx command # Or manually copy component code into src/components/ # 4. Customize the generated code # v0 output is standard React + shadcn/ui + Tailwind # No lock-in, no proprietary components, no runtime dependency ``` ### Iteration ```markdown ## Iterating on v0 Output v0 supports conversation-style iteration: 1. Generate initial component: "A user profile card with avatar, name, bio, stats" 2. Refine: "Make the avatar larger, add an edit button, and add social links" 3. Add variants: "Create a compact version of this card for use in a sidebar" 4. Add interactivity: "Make the bio editable inline with a pencil icon toggle" 5. Responsive: "Make it stack vertically on mobile with the avatar centered" Each iteration builds on the previous — v0 remembers context within a conversation. ``` ### What v0 Generates Well vs What It Doesn't ```markdown ## v0 Strengths - Landing pages, marketing sites - Dashboard layouts, admin panels - Forms (multi-step, with validation UI) - Data tables with filters and pagination - Card layouts, grid systems - Navigation (sidebar, header, breadcrumbs) - Modal dialogs, slide-overs, popovers ## v0 Limitations (handle in your code) - No real API calls (generates mock data) - No authentication logic - No database integration - Complex state management (use React context or Zustand) - Custom animations (add Framer Motion manually) - Server Components vs Client Components (review "use client" placement) ``` ## Examples **Example 1: User asks to set up v0-dev** User: "Help me set up v0-dev for my project" The agent should: 1. Check system requirements and prerequisites 2. Install or configure v0-dev 3. Set up initial project structure 4. Verify the setup works correctly **Example 2: User asks to build a feature with v0-dev** User: "Create a dashboard using v0-dev" The agent should: 1. Scaffold the component or configuration 2. Connect to the appropriate data source 3. Implement the requested feature 4. Test and validate the output ## Guidelines 1. **Be specific with data** — Include actual numbers, labels, and content in prompts; "12,450 users" generates better UI than "user count" 2. **Reference shadcn components** — Mention "shadcn/ui" in prompts; v0 generates cleaner code when explicitly targeting the component library 3. **One component at a time** — Generate individual components, then assemble in Cursor; complex full-page prompts produce worse results 4. **Iterate, don't start over** — Use the conversation to refine; v0 maintains context and each iteration improves on the previous 5. **Review "use client"** — v0 may add `"use client"` unnecessarily; remove it from components that don't use state or effects 6. **Add your design tokens** — After generating, update colors and spacing to match your brand; v0 uses shadcn defaults 7. **Mock data → real data** — v0 generates realistic mock data; replace with API calls once the UI is finalized 8. **No vendor lock-in** — v0 output is standard React code; you own it completely, no runtime dependency on v0
Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".