agentsclimarketplace

Open design landing

Skill nexu-io/open-design/plugins/_official/examples/open-design-landing

🎨 The open-source Claude Design alternative. πŸ–₯️ Local-first desktop app. πŸ–ΌοΈ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video β€” real files, HTML/PDF/PPTX/MP4 export. πŸ€– Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.

Install
npx -y skills add nexu-io/open-design --skill open-design-landing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Γ‰tudes editorial collage) β€” the same aesthetic Open Design uses for its own marketing surface. The agent fills a typed `inputs.json` from a brand brief, optionally generates 16 collage assets via gpt-image-2, then runs a pure-function composer that emits a self-contained HTML file; a separate path can mirror the Astro marketing site in `apps/landing-page/`. Drop-in scroll-reveal motion and a Headroom-style sticky nav are wired automatically.

SKILL.md

13.2 KB, as published. Nobody here has run it

open-design-landing

Build a single-page editorial landing site (or a slide deck β€” see the sibling open-design-landing-deck skill) in the Atelier Zero design system: warm-paper background, Inter Tight + Playfair Display, italic serif emphasis spans, dotted hairline rules, coral terminating dots, scroll-reveal motion, and 16 surreal collage plates.

This is the canonical Open Design marketing-page recipe β€” the example output is the very page you see at open-design.

The skill is fully parameterized. The agent fills one typed inputs.json from the user's brief; the composer turns that JSON + the canonical styles.css into a deployable artifact.

inputs.json + styles.css                       16 image slots
        β”‚                                            β”‚
        └──────────► scripts/compose.ts β—„β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                            β”‚
                            β–Ό
              <out>/index.html  (self-contained)
              <out>/assets/      (PNG or SVG)

What you get

A single HTML file with all of:

  • Editorial topbar (volume / issue / language strip), Headroom-style sticky nav with live GitHub star count.
  • 8 numbered Roman-numeral sections with paper-textured background: hero (with 3 stat rings + 4-step index), about, capabilities (4 cards), labs (5 cards + filter pills + progress bar), method (4 steps with thumbnails), selected work (dark slab + 2 tilted cards), testimonial (pull quote + 5 partner glyphs), CTA (ribbon + email pill).
  • Footer with 4 link columns + huge italic-serif kicker word.
  • Scroll-reveal motion on every section (IntersectionObserver, respects prefers-reduced-motion).
  • Fully responsive at 1280 / 1080 / 880 / 560 breakpoints.

Workflow contract

Run these four steps in order. The agent should complete each step before moving on, and prefer asking the user a focused question over inventing copy.

1. Gather brand inputs

Use AskQuestion (or the equivalent in your UI) to collect the brand brief in chunks; do not dump the entire schema.ts on the user. Map their answers into inputs.json matching the typed shape.

The eight question groups, in order:

GroupSchema fieldsMin answersNotes
1brand.{name,mark,tagline,description,location}5Mark = single glyph (Ø, β–², β˜…β€¦)
2brand.{license,version,year,primary_url,contact_email}4URL is required; license defaults Apache-2.0
3nav[] (up to 5)3Optional count badges
4hero.{label,headline,lead,primary,secondary,stats}AllHeadline as MixedText (sans+em+dot)
5about + capabilities.cards[4]All4 cards Γ— {num,tag,title,body}
6labs.cards[5] + method.steps[4]AllBoth grids fixed-arity
7work.cards[2] + testimonialAll5 partner glyphs as inline SVG path data
8cta + footer.{columns[4],mega}AllMega kicker is a MixedText like the headlines

Open inputs.example.json for a complete worked example (Open Design itself).

2. Decide the image strategy

StrategyWhen to chooseCost / latency
placeholderFirst pass. Demo. Slide internal. No image budget yet.$0, <1s
generateFinal delivery. Brand wants original collages.~$0.40, ~6 min
bring-your-ownUser has art direction PNGs. Drop them at assets_path.$0, 0s

Set inputs.imagery.strategy accordingly.

placeholder β€” frame mode

npx tsx scripts/placeholder.ts <out>/assets/

Writes 16 .svg files (with .png aliases for compatibility) into <out>/assets/. Each placeholder shows the slot id, ratio, pixel dimensions, and the prompt hint from image-manifest.json. The composer's <img src='./assets/hero.png'> etc. just work.

generate β€” gpt-image-2 mode

FAL_KEY=... npx tsx scripts/imagegen.ts <inputs.json> --out=<out>/assets/

Calls fal.ai's openai/gpt-image-2 synchronous endpoint per slot. Composes prompts as: style anchor (paper-collage editorial system)

  • brand variables (name / nav / headline / italic emphasis pulled from inputs.json) + per-slot composition (e.g. cropped plaster head + tree growing through arch). Skips slots whose target file already exists; pass --force to re-render.

Without FAL_KEY, the script prints the prompts so the operator can route them through the /gpt-image-fal slash-command skill manually.

bring-your-own

Drop 16 PNGs matching assets/image-manifest.json filenames at inputs.imagery.assets_path. Done.

3. Compose the artifact

npx tsx scripts/compose.ts <inputs.json> <out>/index.html

The composer reads inputs.json and ../styles.css, then writes one self-contained HTML file. The page includes:

  • The full Atelier Zero stylesheet, inlined.
  • All section markup with data-reveal attributes for staggered scroll motion.
  • Inline IntersectionObserver script (mirrors apps/landing-page/app/_components/reveal-root.tsx).
  • Inline Headroom nav script (mirrors header.tsx).
  • Inline GitHub star-count fetcher (auto-detects from brand.primary_url).

4. (Optional) Mirror the deployable Astro site

For deployable production output, fork the apps/landing-page/ package: copy it into your workspace, align app/page.tsx with content from your inputs.json, and copy your <out>/assets/*.png into the paths expected by app/image-assets.ts / R2 URLs. Build with pnpm --filter @open-design/landing-page build for a static out/ export ready for any CDN.

A future iteration may bundle a composer that emits the full apps/landing-page/ tree from inputs.json in one command. Until then, fork-and-edit is the supported path.


Self-check before delivering

Before marking done, the agent must verify:

  • <out>/index.html opens in a browser without console errors.
  • All 16 image slots load (no 404s in DevTools network tab).
  • Headline italic emphasis spans render in Playfair (not sans).
  • Coral terminating dots appear at every display h1/h2 end.
  • Scroll from top to bottom; every section animates in once.
  • Resize to 880px and 560px; no horizontal scroll, no overlap.
  • prefers-reduced-motion: reduce (DevTools β†’ Rendering) disables transitions cleanly.
  • Lighthouse: contrast AA, font-display swap, no layout shift on the hero (CLS < 0.05).

Files in this skill

design-templates/open-design-landing/
β”œβ”€β”€ SKILL.md                 # this contract
β”œβ”€β”€ README.md                # quick-start
β”œβ”€β”€ schema.ts                # typed inputs (single source of truth)
β”œβ”€β”€ styles.css               # Atelier Zero stylesheet (single source of truth)
β”œβ”€β”€ inputs.example.json      # Open Design as the worked example
β”œβ”€β”€ example.html             # canonical rendering (regenerated from inputs.example.json)
β”œβ”€β”€ scripts/
β”‚   β”œβ”€β”€ compose.ts           # inputs.json + styles.css β†’ index.html
β”‚   β”œβ”€β”€ imagegen.ts          # gpt-image-2 wrapper (fal.ai)
β”‚   └── placeholder.ts       # SVG paper-textured frames
└── assets/
    β”œβ”€β”€ *.png                # 16 collage plates (Open Design instance)
    β”œβ”€β”€ image-manifest.json  # slot β†’ file/dimensions/prompt mapping
    └── imagegen-prompts.md  # human-readable prompt pack

Boundaries

  • Do not invent new colors or typefaces. Tokens live in design-systems/atelier-zero/DESIGN.md; extend the design system before adding a new ramp here.
  • Do not drop data-reveal attributes from generated markup. Without them the page goes static and feels dead.
  • Do not wrap the composed HTML in a framework that injects its own stylesheet ordering β€” Atelier Zero relies on stylesheet-order cascade for paper texture and z-index of side rails.
  • Do not add a separate stylesheet file for the Astro landing-page fork; copy styles.css verbatim into app/globals.css so visual parity stays one-to-one.

See also

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.