← Products

Design
⚙ Needs: a Next.js project with Node.js 18+, the Vercel AI SD…

AI Elements — pre-built AI chat UI components on shadcn/ui

Build AI chat interfaces faster with ai-elements components — conversations, messages, tool displays, and prompt inputs for Next.js apps with shadcn/ui and the Vercel AI SDK

At a glance
What
Build AI chat interfaces faster with ai-elements components — conversations, messages, tool displays, and prompt inputs for Next.js apps with shadcn/ui and the Vercel AI SDK
Cost
Free
Needs
a Next.js project with Node.js 18+, the Vercel AI SDK installed, and shadcn/ui (the ai-elements CLI installs it automatically if missing); a Vercel AI Gateway API key is recommended (small monthly usage credit for model experiments)
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

@
Created by: @mxyhi
⌁

Install

Prerequisites: a Next.js project with Node.js 18+, the Vercel AI SDK installed, and shadcn/ui (the ai-elements CLI installs it automatically if missing); a Vercel AI Gateway API key is recommended (small monthly usage credit for model experiments) Install "AI Elements — pre-built AI chat UI components on shadcn/ui" for me. It gives my agent @mxyhi's AI Elements field guide: check the Node/Next.js/AI SDK/shadcn prerequisites (including the AI Gateway key in env.local), install ai-elements components with the project's own package runner (npx/pnpm dlx/bunx ai-elements@latest), import and compose them as ordinary React components (Message, MessageContent, MessageResponse, conversations, tool displays, prompt inputs — code that lives in the project and can be restyled or extended), fix the usual breakages (Tailwind 4 base styles, missing components.json config, tsconfig path aliases, data-theme switching), and consult the references/ folder for per-component documentation. Apache-2.0 licensed (per the discovery manifest; the repo frontmatter carries no license field). Repository: https://github.com/mxyhi/ok-skills/blob/main/ai-elements/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "ai-elements". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. set up the Next.js + AI SDK + shadcn prerequisites, add the AI Gateway key to env.local, run the ai-elements CLI to pull the components I need). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.