
web-artifacts-builder-v2
Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.
- Installs
- 42
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/sammcj/agentic-coding --skill web-artifacts-builder-v2- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads web-artifacts-builder-v2 automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Web Artefacts Builder
To build a frontend claude.ai artefact, follow these steps:
- Initialise the frontend repo with
scripts/init-artifact.sh - Pick a theme from
resources/themes.cssand apply it (see "Themes" below) - Develop your artefact by editing the generated code
- Bundle to a single HTML file with
scripts/bundle-artifact.sh - Share the bundled artefact with the user
- (Optional) Test the artefact
Stack: React 19 + TypeScript + Vite 8 + Tailwind CSS v4 + shadcn/ui (new-york style) + lucide-react. Bundling via vite-plugin-singlefile. Requires Node 20.19+ or 22.12+.
Design principles
These principles are adapted from the html-design-examples skill. Load that skill alongside this one when you need patterns for specific artefact intents (status report, code review, PR write-up, design system page, editor, etc.); its rendered catalogue at resources/index.html indexes 20 single-file references.
- Calm, editorial aesthetic. Restrained accent colour, generous whitespace, content does the talking. Avoid hero gradients, marketing sheen, and dashboard-style chrome unless the artefact is a dashboard.
- Typography over chrome. Establish hierarchy with weight, size, and leading before reaching for borders, backgrounds, or coloured bars. Serif headings paired with sans body is the recurring pattern in the references and a reliable choice when you have no other signal. Defaulting to Inter as the only typeface is an AI-output tell - pick a pairing from the chosen theme's font notes.
- Earn your accent. Most themes ship with a single accent colour. Treat it as scarce. Use it for the one thing on the page that demands attention (the primary action, the link, the focused state) and almost nowhere else.
- Use the full width when it helps. Don't centre a narrow column when the content is tabular, comparative, or spatial. A wide layout with structured columns reads better than a 720px text shaft for anything that isn't longform prose.
- Export interactive state. If the artefact is an editor, board, or any surface where the user is doing work, finish it with a "copy as JSON" or "copy as prompt" button so the result flows back into the agent loop. See the
18-editor-triage-board.htmlexample inhtml-design-examplesfor the pattern.
Anti-slop rule
Use visual accents (coloured border stripes, tinted-background callout boxes, accent bars on cards) only when the colour or treatment encodes specific information - status, category, severity, or priority that I've explicitly defined. Don't apply visual accents decoratively, don't rotate through palette colours across sibling items for variety, and don't reach for the tinted-callout-with-coloured-bar pattern as a default way to mark asides. If you're about to add an accent, ask whether removing it would lose information; if not, remove it and rely on plain typographic hierarchy instead.
Other things to avoid because they read as AI-default output: excessive centred layouts, purple gradients, uniformly rounded corners on everything, glassmorphism, emoji bullets, and three-card-grid hero sections with identical icons. The same goes for status badges or pulsing dots whose state never changes ("Active", "Verified"), copy that echoes the prompt or stack ("Built with..."), fake-system naming (// separators, SCREAMING_SNAKE labels, version pills, spaced mono-caps eyebrows), and landing-page furniture on working screens (hype subtitles, vanity stat strips, one headline word in the accent colour). Check the alignment of SVGs, ASCII art and timeline markers by measuring the computed boxes.
Themes
resources/themes.css ships five named themes. Pick one before you start writing components - retrofitting a palette is much more work than choosing one up front.
| Theme | Mood | Good for |
|---|---|---|
| Editorial paper | Warm paper, ink, ochre accent | Longform writeups, plans, reports, post-mortems |
| Technical mono | Near-monochrome, single green accent | Code reviews, system diagrams, status pages, debugging |
| Warm desaturated | Sand, clay-brown, muted terracotta | Brand-adjacent artefacts, design pages, anything that wants warmth without volume |
| Cool muted | Quiet slate, low-chroma teal | Dashboards, status reports, technical docs |
| Nordic dark | Polar-night greys, frost-blue | Incident write-ups, debug dumps, dark-mode-first developer tooling |
To apply a theme:
- Read
resources/themes.cssand copy the:root { ... }and.dark { ... }blocks for the chosen theme. - Replace the existing
:rootand.darkblocks in your project'ssrc/index.css. Leave the@theme inlineand@layer baseblocks alone - they wire the variables into Tailwind utilities. - Add the suggested font stack (the comment block above each theme lists one) - either via a
<link rel="stylesheet">tag inindex.htmlfrom Google Fonts, or by settingbody { font-family: ... }insrc/index.css.
If the user has an existing brand or design system, defer to it rather than picking from the gallery.
Quick start
Step 1: Initialise the project
bash scripts/init-artifact.sh <project-name>
cd <project-name>
This creates a configured project with:
- React 19 + TypeScript via Vite 8
- Tailwind CSS v4 (CSS-first config in
src/index.css, notailwind.config.js) - 40+ shadcn/ui components in
src/components/ui/ radix-uiumbrella package and lucide-react- Path alias
@/configured in bothtsconfig.jsonandvite.config.ts - Minimal
App.tsxplaceholder ready for you to edit
Step 2: Apply a theme
See "Themes" above.
Step 3: Develop the artefact
Edit src/App.tsx and add components as needed. Components are imported from @/components/ui/<name>. The cn() helper lives at @/lib/utils.
To preview during development:
pnpm dev
Step 4: Bundle to a single HTML file
bash scripts/bundle-artifact.sh
This produces bundle.html - a single self-contained file with all JS, CSS, and assets inlined. The script:
- Adds
vite-plugin-singlefileas a dev dependency - Writes a
vite.config.bundle.tsthat extends your config with the single-file plugin and inlining options - Runs
vite build --config vite.config.bundle.ts - Renames
dist/index.htmltobundle.html
The artefact requires nothing at runtime - hand it to the user directly.
Step 5: Share with the user
Pass bundle.html back to the user as the artefact.
Step 6: Test (optional)
Only test before sharing if the user has asked, or if the artefact has interactive logic that you don't want to ship broken. Use Playwright or open the file locally. Otherwise prefer shipping fast and iterating on feedback.
Reference
- shadcn/ui components: https://ui.shadcn.com/docs/components
- Tailwind CSS v4 docs: https://tailwindcss.com/docs
- Companion skill for design patterns:
html-design-examples
FAQ
What does the web-artifacts-builder-v2 skill do?
Suite of tools for creating elaborate, multi-component claude.ai HTML artefacts using modern frontend web technologies (React 19, Tailwind CSS v4, shadcn/ui). Use for complex artefacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artefacts.
How do I install web-artifacts-builder-v2?
Run npx skills add https://github.com/sammcj/agentic-coding --skill web-artifacts-builder-v2 in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/web-artifacts-builder-v2/ (personal) or .claude/skills/web-artifacts-builder-v2/ (project).
Which AI agents can use web-artifacts-builder-v2?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is web-artifacts-builder-v2 safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains web-artifacts-builder-v2?
It is published by sammcj in sammcj/agentic-coding. It has 42 recorded installs.
More from sammcj/agentic-coding
critical-thinking-logical-reasoning
sammcj/agentic-coding
Critically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when explicitly asked to critically analyse or critique an argument.
writing-documentation-with-diataxis
sammcj/agentic-coding
Applies the Diataxis framework to create or improve technical documentation. Use when being asked to write high quality tutorials, how-to guides, reference docs, or explanations, when reviewing documentation quality, or when deciding what type of documentation to create. Helps identify documentation types using the action/cognition and acquisition/application dimensions.
creating-development-plans
sammcj/agentic-coding
Creates structured development plans with phased task breakdowns, requirements, and QA checklists. Use when the user explicitly asks to create a dev plan, development plan, or document development requirements.
ghostty-config
sammcj/agentic-coding
Open the skill to read its SKILL.md instructions.
code-simplification
sammcj/agentic-coding
Open the skill to read its SKILL.md instructions.
prompt-enhancer
sammcj/agentic-coding
Open the skill to read its SKILL.md instructions.
Popular frontend & design skills
setup-matt-pocock-skills
mattpocock/skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
frontend-design
anthropics/skills
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
hyperframes-animation
heygen-com/hyperframes
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.
prototype
mattpocock/skills
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
hyperframes-core
heygen-com/hyperframes
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.
vercel-react-best-practices
vercel-labs/agent-skills
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.