Use for distinctive production-grade websites, landing pages, and interactive web experiences with strong design and QA discipline.
beeuni marketplace install beeuni-starter:website-buildingbun run shared/generate-palette.ts "keywords") to create a unique color scheme for each project. NEVER reuse the same palette across sites.skills/webapp/SKILL.md.design-foundations. This skill's shared files extend those foundations with web-specific implementation (CSS variables, responsive tokens, base stylesheets). You don't need to load design-foundations separately — the web-specific versions in shared/ are comprehensive.read with the full path, e.g. skills/website-building/shared/01-design-tokens.md| Project Type | Action | Examples |
|---|---|---|
| Informational sites | read skills/website-building/informational/informational.md | Personal sites, portfolios, editorial/blogs, small business, landing pages |
| Web applications | read skills/webapp/SKILL.md | SaaS products, dashboards, admin panels, e-commerce, brand experiences |
| Browser games | read skills/website-building/game/game.md + skills/website-building/game/game-testing.md | 2D Canvas games, Three.js/WebGL, HTML5 games, interactive 3D experiences |
skills/website-building/shared/01-design-tokens.md and skills/website-building/shared/02-typography.md first (mandatory for ALL project types, including webapp). These establish the Beeuni design system defaults and typography rules that apply universally. For web applications and dashboards, skip files marked with † below — those contain implementation details pre-configured in the fullstack template.shared/) — Every project| File | Covers | Load |
|---|---|---|
shared/01-design-tokens.md | Type scale, spacing, Beeuni palette, base.css | Always |
shared/02-typography.md | Font selection, pairing, loading, blacklist | Always |
shared/04-layout.md | Spatial composition, responsive, mobile-first | Always † |
shared/05-taste.md | Skeleton loaders, empty/error states, polish | Always |
shared/08-standards.md | Accessibility, performance, anti-patterns | Always |
shared/09-technical.md | Project structure, sandbox, deploy, checklist | Always † |
shared/head-defaults.html | Attribution block for <head> | Always † |
shared/03-motion.md | Scroll animations, Motion library, GSAP SVG plugins, hover/cursor | When animated |
shared/06-css-and-tailwind.md | Tailwind CSS v3, shadcn/ui, modern CSS | When using Tailwind |
shared/07-toolkit.md | CDN libraries, React, Three.js, icons, maps, SVG patterns/filters, esm.sh | When choosing libs |
shared/10-charts-and-dataviz.md | Chart.js, Recharts, D3, KPIs, sparklines | When data viz needed |
shared/11-web-technologies.md | Framework versions, browser compatibility | When checking compat |
shared/12-playwright-interactive.md | Persistent Playwright browser QA, screenshots, visual testing | When testing |
shared/19-backend.md | FastAPI/Express/Flask servers, WebSocket, SSE, port forwarding | When backend needed |
shared/20-llm-api.md | LLM/AI API integration reference | When site uses AI APIs |
skills/website-building/.| File | When to load |
|---|---|
read skills/webapp/SKILL.md | SaaS, dashboard, admin, e-commerce, brand experience (fullstack template skill) |
skills/webapp/dashboards.md | Dashboard or data-dense interface (companion to webapp) |
informational/informational.md | Personal site, portfolio, editorial, small business, landing |
game/game.md | Browser game, Three.js, WebGL, interactive 3D |
game/2d-canvas.md | 2D Canvas game (companion to game.md) |
game/game-testing.md | Any browser game — load alongside game.md |
skills/website-building/shared/12-playwright-interactive.md for persistent browser automation with Playwright (screenshots, functional testing, visual QA). Required for game testing, useful for any complex site.read("skills/website-building/shared/01-design-tokens.md")
read("skills/website-building/shared/02-typography.md")
read("skills/website-building/shared/04-layout.md")
read("skills/website-building/shared/05-taste.md")
read("skills/website-building/shared/08-standards.md")
bun run skills/website-building/shared/generate-palette.ts "subject keywords here"
pty_spawn, then show its plain URL:# static site (no build step)
python3 -m http.server 3000 --directory /workspace/project
# app: run its dev server instead, e.g. npm run dev
show(type: "url", url: "http://localhost:3000/"). The platform auto-detects and proxies any localhost port — no special URL format needed.skills/website-building/shared/12-playwright-interactive.md to screenshot at desktop (1280px+) and mobile (375px). Compare against references. This is mandatory, not optional. See Visual QA below.currentColor for dark/light mode.aria-label, viewBox, fill="none", currentColor strokesshared/03-motion.md. For SVG patterns/filters, see shared/07-toolkit.md.skills/website-building/shared/12-playwright-interactive.md for all visual QA. Playwright provides a persistent browser session for screenshots, interaction testing, and viewport verification.Build → Playwright QA → Evaluate → Fix → Repeat → Deploy when readyinformational.md, webapp/SKILL.md, game/game.md) has an Art Direction table mapping site/product types to concept-driven directions and token starting points. Use these as a springboard.skills/website-building/shared/01-design-tokens.md with:--text-3xl/--text-hero are for informational site heroes only.skills/website-building/shared/08-standards.md for the full anti-patterns list.skills/website-building/shared/09-technical.md for the recommended preview and delivery flow.web-publishing-and-deployments skill. It owns the whole publish path: the guardrail (explicit user opt-in — never publish unprompted), runtime-only dependencies that won't survive a standalone deployment, the mandatory pre-publish security review, and the provider mechanics.pty_spawn for the preview or dev server.Get a complete picture of any company or person before outreach. This skill always works with web search, and gets significantly better with enrichment and CRM data.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Route code, repository, and data/SQL work to isolated Beeuni sessions instead of burning your main context on it. Use when asked to implement a feature, fix a bug, make failing tests pass, work a ticket/issue, refactor, navigate or change a codebase, ship a PR, review a pull request, or run SQL/warehouse analysis against a dataset — and when the user wants two agents or parallel reviewers/investigators on the same work. Covers the explore-vs-session routing call, deciding where the code lives (this project's repo vs cloning an external GitHub repo) or where the data lives, finding the repo with gh, spawning sessions in parallel, dual PR reviews, and reporting results back. Triggers: 'implement', 'fix the bug', 'make the tests pass', 'work this ticket', 'refactor this', 'open a PR', 'review this PR', 'run two agents on it', 'query the warehouse', 'analyze this dataset'.
Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF you cannot read directly.
Deep research agent skill. Use when the user needs thorough, scientific, truth-seeking research on any topic -- investigating claims, finding primary sources, synthesizing evidence, producing cited reports. Triggers on: 'research this', 'investigate', 'deep dive', 'find sources', 'what does the evidence say', 'literature review', 'fact check', 'analyze the research on', any request requiring multi-source investigation with citations.
Artifact-agnostic design guidance — works for CSS, PowerPoint, matplotlib, PDF, or any visual output. Also includes a curated catalog of named font/color themes for slides, docs, and reports (non-web assets).