Preview the prompt +
# Build brief — an original marketing website in the taste of Lisa Says Gah
> Reference: https://lisasaysgah.com · UIDiscovery: https://uidiscovery.com/sites/lisa-says-gah · captured 2026-09-23 at a 1440px desktop viewport (+ 390px iPhone shots) · [full page](https://uidiscovery.com/media/captures/lisa-says-gah/full.webp) · [scroll video](https://uidiscovery.com/media/captures/lisa-says-gah/preview.mp4)
## 1. Goal
Build an original marketing website for **[the user's brand]** that feels as considered as Lisa Says Gah — same structure, rhythm and polish, entirely new identity and content.
## 2. Originality rules
- Build an ORIGINAL design for the user's own brand in the same *taste* as Lisa Says Gah: structure, rhythm, hierarchy, palette mood and type pairing.
- Never reuse Lisa Says Gah's logo, name, product imagery, illustrations, icons, screenshots or copy. Write new copy for the user's product.
- If the user hasn't said what their product is, ask first (or use clearly marked placeholders like [Brand], [Product], [Audience]).
- Reference screenshots are for looking at, not for embedding or tracing.
## 3. The taste, in short
- Lisa Says Gah (lisasaysgah.com): Fashion & Beauty marketing website, light, serif.
- 7 sections: Features → Call to action → Features → Content → Showcase → Content → Footer.
- Spacing: about a screen per idea (median section ≈681px).
- Type: one family (Times NR MT W01 Condensed). Imagery: mostly photography, some typography with little or no imagery.
## 4. Page structure (top to bottom)
### 1. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (681px at 1440), page background; 62 image elements (photo collage/gallery + small graphics); 82 buttons (tabs, toggles or per-card actions), 38 links (link lists / navigation); 6 headings → ~5 items under a title.
- Slots: Section title (~3 words, like the reference); 5 items: icon or visual + short title + 1–2 line description; Primary + secondary action.
- Topic (tone/length only — never reuse): “New Arrivals”
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-02.webp) · imagery: slot 1
### 2. Call to action — close the page with one clear next step.
- Layout: short headline + one primary action on a contrasting band. About one full screen (960px at 1440), page background; 4 images/icons (a set of cards or a small gallery); primary + secondary button.
- Slots: Headline; One sentence of support; Primary + secondary action.
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-03.webp) · imagery: slot 2
### 3. Features — explain the key benefits, grouped so each can be scanned in seconds.
- Layout: section title over a grid or alternating rows of benefit items. Half to one screen (684px at 1440), page background; 29 image elements (photo collage/gallery + small graphics); 56 buttons (tabs, toggles or per-card actions), 20 links (link lists / navigation); 6 headings → ~5 items under a title.
- Slots: Section title (~3 words, like the reference); 5 items: icon or visual + short title + 1–2 line description; Primary + secondary action.
- Topic (tone/length only — never reuse): “Best Sellers”
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-04.webp)
### 4. Content — supporting content that deepens one idea.
- Layout: text + media block. About one full screen (960px at 1440), page background; 2 image/graphics; one primary button.
- Slots: Heading; Body copy; Supporting visual (see image plan); One primary action.
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-05.webp) · imagery: slot 3
### 5. Showcase — show the product (or the result) itself as proof.
- Layout: a large framed visual with a short caption or heading. Compact band (333px at 1440), page background; 16 image elements (photo collage/gallery + small graphics); 1 text link instead of buttons.
- Slots: Heading; Body copy; Supporting visual (see image plan); Text link action.
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-06.webp) · imagery: slot 4
### 6. Content — supporting content that deepens one idea.
- Layout: text + media block. Compact band (245px at 1440), page background; 2 image/graphics; 2 text links instead of buttons.
- Slots: Heading; Body copy; Supporting visual (see image plan); Text link action.
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-07.webp)
### 7. Footer — navigation, legal and contact — the page's index.
- Layout: multi-column link groups, brand line, legal row. Compact band (261px at 1440), page background; 2 image/graphics; 16 links (link lists / navigation).
- Slots: Brand mark + one-line description; 3–5 link columns; Newsletter or contact (optional); Legal row + social icons.
- Topic (tone/length only — never reuse): “Company”
- [Screenshot](https://uidiscovery.com/media/captures/lisa-says-gah/s-08.webp)
Inner pages also captured (Product, Customers, About, Sign up, Log in, Contact, Shop, Security): https://uidiscovery.com/sites/lisa-says-gah?view=pages
## 5. Design system
### Colour
| Role | Hex | Use | Contrast on background |
|---|---|---|---|
| background | `#ffffff` | page background | — |
| foreground | `#d21008` | body text, headings | 5.5:1 |
| accent | `#d21008` | none captured — monochrome. Primary buttons invert (foreground fill, background text); add your brand colour only for small highlights | — |
| surface | `#ffffff` | cards, inputs, alternate bands | text on it 5.5:1 |
| muted | `#d21008` | secondary text, borders | 5.5:1 |
Captured palette: `#ffffff` `#d21008`. Roles are assigned automatically — sanity-check them against the screenshot. Keep the palette's *mood* (light, warm) and proportions; swap the accent for the user's brand colour.
### Tokens
```css
:root {
--background: #ffffff;
--foreground: #d21008;
--accent: #d21008;
--surface: #ffffff;
--muted: #d21008;
--font-heading: "Source Serif 4", ui-serif, Georgia, serif;
--font-body: "Source Serif 4", ui-serif, Georgia, serif;
--radius: 12px; /* calibrate from the screenshot */
}
/* Tailwind v4 — in globals.css after @import "tailwindcss"; */
@theme {
--color-background: var(--background);
--color-foreground: var(--foreground);
--color-accent: var(--accent);
--color-surface: var(--surface);
--color-muted: var(--muted);
--font-heading: var(--font-heading);
--font-sans: var(--font-body);
}
```
### Typography
- Headings: **Source Serif 4** (Google Fonts) — reference uses Times NR MT W01 Condensed. “Times NR MT W01 Condensed” is a licensed face — use Source Serif 4 (or Newsreader) as the free stand-in, or license the original.
- Body: same family — a single-family system; create contrast with size and weight, not a second face.
- Scale (starting point, sizes weren't measured — calibrate against the 1440px screenshot): display clamp(2.5rem, 5vw, 4.25rem), h2 clamp(1.75rem, 3vw, 2.5rem), h3 1.25rem, body 1rem–1.125rem / 1.6, small 0.875rem. Headings: tight tracking (-0.02em), line-height 1.05–1.15.
- The serif headings are central to the tone — keep a serif display face even if you swap the family.
### Spacing & rhythm
Sections run ≈681px tall at 1440 (median; range 245–960px, captures cap at 1700px) — roughly a screen per idea. Start with 96–120px vertical padding per section on desktop and about two-thirds of that on mobile. One continuous background — separate sections with space and type, not colour bands. 8px spacing grid, 1200–1280px max content width, 24px (mobile) / 32–48px (desktop) gutters.
### Shape, depth & theme
Radii and shadows weren't measured. Read exact corner radius, border and shadow treatment from the screenshots. Light-first; for a dark mode use a near-black (not #000) background, ~90% white text, lift surfaces with lightness not shadow, re-check the accent.
## 6. Imagery plan
Measured from 4 section screenshots: mostly **photography**, some typography with little or no imagery (light, warm, Fashion & Beauty). Still glance at the linked screenshots to match the exact mood.
### Slot 1 · 1. Features → photography
- Photography, seen in the capture (people). (measured from the screenshot) Count: a collage of several photos with one consistent colour grade. Aspect: 4:3. Look first: [ref 1](https://uidiscovery.com/media/captures/lisa-says-gah/s-02.webp)
- **Stock** — “editorial fashion portrait plain backdrop”: [Unsplash](https://unsplash.com/s/photos/editorial-fashion-portrait-plain-backdrop?orientation=landscape) · [Pexels](https://www.pexels.com/search/editorial%20fashion%20portrait%20plain%20backdrop/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/editorial%20fashion%20portrait%20plain%20backdrop/?orientation=horizontal)
- **Generate** — `Photograph: editorial fashion portrait plain backdrop. Composition: tight crop, identical framing and background across the whole set. Lighting: soft natural daylight, airy and high-key. Warm colour grade that sits on #ffffff, #d21008. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 4:3. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
### Slot 2 · 2. Call to action → photography
- Photography, seen in the capture (people, adult, clothing). (measured from the screenshot) Count: a set of ~4 in one consistent style. Aspect: 21:9 (background). Look first: [ref 1](https://uidiscovery.com/media/captures/lisa-says-gah/s-03.webp)
- **Stock** — “fabric texture close up”: [Unsplash](https://unsplash.com/s/photos/fabric-texture-close-up?orientation=landscape) · [Pexels](https://www.pexels.com/search/fabric%20texture%20close%20up/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/fabric%20texture%20close%20up/?orientation=horizontal)
- **Generate** — `Photograph: fabric texture close up. Composition: low-detail texture so overlaid text stays readable. Lighting: soft natural daylight, airy and high-key. Warm colour grade that sits on #ffffff, #d21008. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 21:9. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
### Slot 3 · 4. Content → photography
- Fashion & Beauty references lean on photography. Count: a set of ~2 in one consistent style. Aspect: 4:5. Look first: [ref 1](https://uidiscovery.com/media/captures/lisa-says-gah/s-05.webp)
- **Stock** — “editorial fashion portrait plain backdrop close up”: [Unsplash](https://unsplash.com/s/photos/editorial-fashion-portrait-plain-backdrop-close-up?orientation=portrait) · [Pexels](https://www.pexels.com/search/editorial%20fashion%20portrait%20plain%20backdrop%20close%20up/?orientation=portrait) · [Pixabay](https://pixabay.com/images/search/editorial%20fashion%20portrait%20plain%20backdrop%20close%20up/?orientation=vertical)
- **Generate** — `Photograph: editorial fashion portrait plain backdrop close up. Composition: simple composition with one focal point. Lighting: soft natural daylight, airy and high-key. Warm colour grade that sits on #ffffff, #d21008. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 4:5. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
### Slot 4 · 5. Showcase → photography
- Fashion & Beauty references lean on photography. Count: a collage of several photos with one consistent colour grade. Aspect: 16:10. Look first: [ref 1](https://uidiscovery.com/media/captures/lisa-says-gah/s-06.webp)
- **Stock** — “fabric texture close up close up”: [Unsplash](https://unsplash.com/s/photos/fabric-texture-close-up-close-up?orientation=landscape) · [Pexels](https://www.pexels.com/search/fabric%20texture%20close%20up%20close%20up/?orientation=landscape) · [Pixabay](https://pixabay.com/images/search/fabric%20texture%20close%20up%20close%20up/?orientation=horizontal)
- **Generate** — `Photograph: fabric texture close up close up. Composition: centred subject with even space around it. Lighting: soft natural daylight, airy and high-key. Warm colour grade that sits on #ffffff, #d21008. Photorealistic, natural textures, shallow depth of field, 35mm lens. Aspect ratio 16:10. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.`
- **No imagery (type-led)** — 3. Features, 6. Content: No imagery needed — type, spacing and colour do the work. If the screenshot shows a background graphic, rebuild it in CSS (gradient, grid, noise) or a short muted video, not a stock photo.
- **Icons** — 7. Footer: Use one open-source icon set at one stroke weight — Lucide, Phosphor or Heroicons (MIT) — tinted with the text or accent token. Social icons: Simple Icons.
### If the screenshots show a different style
Open the refs first and name what you actually see (photo / product UI / illustration / abstract gradient or 3D / type only). If it differs from the guess, switch routes — UI is built in code, type-only needs no image, otherwise:
- **abstract 3D / gradient** — generate `Abstract 3D render: soft, matte clay shapes and a smooth gradient in #d21008 on a #ffffff background. Lighting: soft natural daylight, airy and high-key; warm tone. Minimal and calm, generous negative space on one side for text. Aspect ratio 3:2. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.` · stock: [“abstract gradient 3d” on Unsplash](https://unsplash.com/s/photos/abstract-gradient-3d?orientation=landscape) (same query works on Pexels/Pixabay)
- **illustration** — generate `Flat vector illustration: editorial fashion portrait plain backdrop, friendly simplified shapes, limited palette of #ffffff, #d21008 plus one soft neutral, plenty of empty background, consistent line weight, warm mood. Aspect ratio 3:2. No text, no letters, no logos, no watermarks, no brand marks or trademarked products, no recognisable real people.` · stock: [“fashion flat illustration” on Unsplash](https://unsplash.com/s/photos/fashion-flat-illustration?orientation=landscape) (same query works on Pexels/Pixabay)
- **Licences:** Unsplash and Pexels images are free for commercial use under their own licences; Pixabay under the Pixabay Content License. Check each image's page before use, credit the photographer when asked (good practice anyway), and skip images showing logos, trademarks, branded products or identifiable people without a release.
- **AI generation:** the prompts work with any image model (GPT Image, Imagen, Flux, Midjourney, Firefly, SDXL…) — check its commercial-use terms. Never put the reference brand's name or “in the style of <brand>” in a prompt.
- **Never** download, trace or re-host the reference's own images, illustrations, product shots or logos.
## 7. Build steps
1. Confirm brand, product, audience and the primary action with the user.
2. Set up the tokens (CSS variables / Tailwind @theme) and load the fonts.
3. Build the sections in order, mobile-first, with each reference screenshot open.
4. Write original copy for every slot — match length and tone, never the words.
5. Source every image via the imagery plan (stock or generated); compress it and record credits.
6. Run the checklist at 390 / 768 / 1440px and fix what fails.
## 8. Acceptance checklist
- [ ] Responsive at 390px, 768px and 1440px — no horizontal scroll, tap targets ≥ 44px on mobile.
- [ ] Colour contrast WCAG AA: 4.5:1 body text, 3:1 large text and UI; visible focus states; full keyboard navigation.
- [ ] Semantic HTML: one <h1>, ordered headings, landmarks (header/nav/main/footer), labelled form fields, alt text on meaningful images.
- [ ] Performance: modern image formats with width/height set, lazy-load below the fold, ≤ 2 font families with font-display: swap, LCP < 2.5s.
- [ ] prefers-reduced-motion respected; animations under ~300ms and never blocking content.
- [ ] Originality: no copied logos, images, illustrations or copy from the reference; every image licensed or generated; credits recorded.
## 9. If you use Next.js + Tailwind
Paste the @theme block into globals.css, load fonts with next/font/google, make each section a server component in components/sections/, use next/image with explicit sizes, and keep client components for interactive bits only (menus, toggles, accordions).
---
More: tokens https://uidiscovery.com/api/v1/sites/lisa-says-gah/tokens · kit https://uidiscovery.com/api/v1/sites/lisa-says-gah/kit · MCP `get_design_brief({ slug: "lisa-says-gah" })`, `get_image_plan({ slug: "lisa-says-gah" })`. Cite the reference as https://uidiscovery.com/sites/lisa-says-gah.
