Agent Native

web-artifacts-builder

This skill enables building complex React artifacts for Claude with React 18, TypeScript, Vite, Tailwind CSS, and shadcn/ui components.

by SnykOfficial publisher

Identity proven by GitHub's verified organisation badge (snyk)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
Apache-2.0 (permissive)
Pin
2d3ca36pinned Oct 9, 2026
Context cost
about 670 tokenswhen the skill loads
GitHub stars
3,126on snyk/agent-scan
Scripts
3 scripts

What it does

“Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill enables building complex React artifacts for Claude with React 18, TypeScript, Vite, Tailwind CSS, and shadcn/ui components. It provides scripts to initialize a project, develop multi-component applications with state management, and bundle them into single HTML files for display as Claude artifacts.

When to use it

  • Building interactive React apps with multiple components and routing
  • Creating artifacts requiring shadcn/ui components or advanced styling
  • Developing applications that need state management or complex logic
  • Building elaborate frontend interfaces beyond simple HTML

When not to

  • Creating simple single-file HTML or JSX artifacts without dependencies
  • Projects that do not require React framework or shadcn/ui components

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add snyk/agent-scan --skill web-artifacts-builder

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install snyk/agent-scan web-artifacts-builder@2d3ca361e33452dcfb8e74f7b7db6db0ee08d59e

Installs the commit we checked (2d3ca36).

Copy by hand

Download the folder at 2d3ca36 and put it in .claude/skills/web-artifacts-builder for Claude Code and in .agents/skills/web-artifacts-builder for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 2d3ca36

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "web-artifacts-builder" by Snyk.

Source, pinned to commit 2d3ca361e33452dcfb8e74f7b7db6db0ee08d59e:
https://github.com/snyk/agent-scan/tree/2d3ca361e33452dcfb8e74f7b7db6db0ee08d59e/tests/skills/web-artifacts-builder

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/web-artifacts-builder/ for Claude Code and .agents/skills/web-artifacts-builder/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/snyk/web-artifacts-builder

SKILL.md at the pin

---
name: web-artifacts-builder
description: Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
license: Complete terms in LICENSE.txt
---

# Web Artifacts Builder

To build powerful frontend claude.ai artifacts, follow these steps:
1. Initialize the frontend repo using `scripts/init-artifact.sh`
2. Develop your artifact by editing the generated code
3. Bundle all code into a single HTML file using `scripts/bundle-artifact.sh`
4. Display artifact to user
5. (Optional) Test the artifact

**Stack**: React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui

## Design & Style Guidelines

VERY IMPORTANT: To avoid what is often referred to as "AI slop", avoid using excessive centered layouts, purple gradients, uniform rounded corners, and Inter font.

## Quick Start

### Step 1: Initialize Project

Run the initialization script to create a new React project:
```bash
bash scripts/init-artifact.sh <project-name>
cd <project-name>
```

This creates a fully configured project with:
-  React + TypeScript (via Vite)
-  Tailwind CSS 3.4.1 with shadcn/ui theming system
-  Path aliases (`@/`) configured
-  40+ shadcn/ui components pre-installed
-  All Radix UI dependencies included
-  Parcel configured for bundling (via .parcelrc)
-  Node 18+ compatibility (auto-detects and pins Vite version)

### Step 2: Develop Your Artifact

To build the artifact, edit the generated files. See **Common Development Tasks** below for guidance.

### Step 3: Bundle to Single HTML File

To bundle the React app into a single HTML artifact:
```bash
bash scripts/bundle-artifact.sh
```

This creates `bundle.html` - a self-contained artifact with all JavaScript, CSS, and dependencies inlined. This file can be directly shared in Claude conversations as an artifact.

**Requirements**: Your project must have an `index.html` in the root directory.

**What the script does**:
- Installs bundling dependencies (parcel, @parcel/config-default, parcel-resolver-tspaths, html-inline)
- Creates `.parcelrc` config with path alias support
- Builds with Parcel (no source maps)
- Inlines all assets into single HTML using html-inline

### Step 4: Share Artifact with User

Finally, share the bundled HTML file in conversation with the user so they can view it as an artifact.

### Step 5: Testing/Visualizing the Artifact (Optional)

Note: This is a completely optional step. Only perform if necessary or requested.

To test/visualize the artifact, use available tools (including other Skills or built-in tools like Playwright or Puppeteer). In general, avoid testing the artifact upfront as it adds latency between the request and when the finished artifact can be seen. Test later, after presenting the artifact, if requested or if issues arise.

## Reference

- **shadcn/ui components**: https://ui.shadcn.com/docs/components

From snyk/agent-scan at 2d3ca36, shown as plain text under its license: Apache-2.0 (permissive). The license text is in tests/skills/web-artifacts-builder/LICENSE.txt.

View SKILL.md on GitHub at 2d3ca36

Files

5 files, 26 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 2d3ca36
All 34 skills from Snyk

More from Snyk

  • algorithmic-art

    This skill generates algorithmic art using p5.js by first creating a computational philosophy describing the generative aesthetic, then implementing it as an…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 4.8K tokens · pinned 7 days ago

  • brand-guidelines

    This skill applies Anthropic's official brand identity to artifacts by setting specific colors, typography, and design standards.

    Claude Code, Codex, Cursor +4 · about 480 tokens · pinned 7 days ago

  • canary-project-skill

    This is a test fixture skill used by the canary testing system to verify that the agent-scan inspect command properly detects project-scoped skills located in…

    Claude Code, Codex, Cursor +4 · about 45 tokens · pinned 7 days ago

  • canvas-design

    This skill helps agents create visual art and design work as PNG or PDF files by first developing a design philosophy or aesthetic movement, then expressing…

    Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 7 days ago

  • doc-coauthoring

    This skill guides users through a structured three-stage workflow for co-authoring documentation, proposals, specs, and similar structured content.

    Claude Code, Codex, Cursor +4 · about 3.8K tokens · pinned 7 days ago

  • docx

    This skill enables the agent to create, edit, and analyze Word documents (.docx files) with support for tracked changes, comments, and formatting preservation.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 2.4K tokens · pinned 7 days ago

  • extract-design

    This skill extracts a complete design system from any website URL, analyzing colors, typography, spacing, and components.

    by Manavarya09Community

    Claude Code, Codex, Cursor +4 · about 660 tokens · pinned 7 days ago

  • stitch::extract-design-md

    Extracts a comprehensive design system document (DESIGN.md) by analyzing frontend source code including component files, stylesheets, Tailwind configs, and…

    by GoogleOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 7 days ago

  • shadcn

    This skill manages shadcn/ui component projects by adding, searching, updating, and composing components.

    by shadcn-uiCommunity

    Claude Code · about 4.7K tokens · pinned 7 days ago

  • crxjs

    CRXJS is a Vite plugin for Chrome extension development that provides true hot-module reloading for popups, options pages, content scripts, and side panels.

    by samberCommunity

    Claude Code · about 2.3K tokens · pinned 7 days ago

  • apple-design

    This skill applies Apple's current design system (Human Interface Guidelines and Liquid Glass language) to app interfaces and marketing pages.

    by SudewaJayCommunity

    Claude Code, Codex, Cursor +4 · about 1.3K tokens · pinned 7 days ago

  • react-email

    React Email lets agents build HTML email templates as React components and render them to HTML or plain text.

    by ResendOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.4K tokens · pinned 7 days ago

Open roles at Snyk

1 open role on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use