Premium Saas Design logo

Premium Saas Design

Community
HermeticOrmus
premium-saas-design

Professional framework for building premium $5k+ SaaS websites with AI - the Define, Build, Review, Refine loop used by real product teams

Overview

PublisherHermeticOrmus
RepositoryLibreUIUX-Claude-Code
Skill namepremium-saas-design
Stars
104
Forks
18
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by HermeticOrmus on GitHub. Read the source before you install it.

Installation

Install the Premium Saas Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git /tmp/LibreUIUX-Claude-Code
mkdir -p .claude/skills
cp -r /tmp/LibreUIUX-Claude-Code/plugins/design-mastery/skills/premium-saas-design .claude/skills/premium-saas-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Premium Saas Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Premium Saas Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Premium Saas Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Premium SaaS Design Framework

"75% of users won't trust a company if the design doesn't look good."

This skill captures the professional design workflow used by senior product teams and UI/UX designers, adapted for AI-assisted development. The framework transforms AI from a "guessing machine" into a true design partner.


The Core Loop

DEFINE → BUILD → REVIEW → REFINE
   ↑                        │
   └────────────────────────┘

This loop is everything. It's used by real product teams and works wonders with AI.


The 7 Context Artifacts

AI needs context to produce premium results. These 7 documents form your "design contract" with AI:

1. Project Brief

What: Single document explaining what you're building, why, and for whom. Purpose: Gives AI direction and understanding of the project.

markdown
# Project Brief: [Product Name]

## What We're Building
[Description of the product/website]

## Primary Target Audience
- [Persona 1]: [Description]
- [Persona 2]: [Description]

## Goals
1. [Primary goal - e.g., drive signups]
2. [Secondary goal - e.g., build trust]
3. [Tertiary goal - e.g., explain the product]

## Requirements
- Fully responsive (mobile-first)
- Blazing fast performance
- Accessible (WCAG 2.1 AA)
- [Other requirements]

## Sections
1. Hero
2. Trust Logos
3. Features
4. [etc.]

Key Insight: Think of AI as a new team member. You wouldn't tell them "build me a website" without context.


2. Content Files (One Per Section)

What: Separate file for each section containing all copy/content. Purpose: Focuses AI on content separately from design.

markdown
# Hero Section Content

## Headline
[Main headline text]

## Subheadline
[Supporting text]

## CTA Primary
Text: [Button text]
Action: [What happens on click]

## CTA Secondary
Text: [Link text]
Action: [What happens on click]

## Social Proof (optional)
[Trust indicators, stats, etc.]

3. General Vibe Mood Board

What: Visual inspiration for the overall site aesthetic. Purpose: Answers "What should the whole site FEEL like when we land on it?"

markdown
# General Vibe

## Overall Aesthetic
- Theme: [Dark/Light/Mixed]
- Feel: [Modern, Professional, Playful, etc.]
- Color Direction: [Primary color family and why]

## Inspiration References

### Reference 1: [Site Name]
- URL: [link]
- What I Like:
  - [Specific element 1]
  - [Specific element 2]
- Screenshot: [embedded image]

### Reference 2: [Site Name]
- URL: [link]
- What I Like:
  - [Specific element 1]
  - [Specific element 2]
- Screenshot: [embedded image]

## Color Psychology
- Primary Color: [Color] - [Why this color for this audience]
  Example: Turquoise/blue evokes professionalism and trust (important for security products)

## Typography Direction
- Headlines: [Font family, weight, style]
- Body: [Font family, size range]

Research Sources:

  • Dribbble (search "[industry] SaaS landing page")
  • Awwwards
  • SaaS Landing Page examples
  • Competitor sites

4. Section-Specific Mood Boards

What: Detailed specs for each section - the "Frankenstein" approach. Purpose: Gives AI precise visual direction for every section.

markdown
# Hero Section Specs

## Layout Reference
- URL: [Reference site]
- Screenshot: [embedded]
- What to Copy:
  - Text alignment: [left/center/right]
  - Font hierarchy
  - Button placement

## Navigation Bar
### Components
- Logo: [Position, size]
- Menu Links: [Style, hover effects]
- CTA Button: [Shape, color, glow effects]

### Code Reference (from component library)
```tsx
// Include actual component code from shadcn/21st.dev

Hero Content Area

Layout

  • [Left/Right/Center aligned]
  • [Split layout description]

3D Element (if applicable)

  • Source: [Three.js / Sketchfab link]
  • Position: [Where in layout]
  • Animation: [Type of movement]
  • Code:
tsx
// Include Three.js or animation code

Components from Libraries

Primary Button

  • Source: 21st.dev
  • Style: [pill shaped, glow outline, etc.]
  • Code:
tsx
// Component code

Background Effects

  • Type: [Gradient, particles, grid, etc.]
  • Source: [Library link]
  • Code:
tsx
// Effect code

Animations

  • Scroll Effects: [Parallax, fade-in, etc.]
  • Hover States: [What elements animate]
  • Entrance Animations: [Staggered, sequential, etc.]

**Critical**: Be VERY granular. This is where premium separates from generic.

---

### 5. Style Guide (Living Document)
**What**: Single source of truth for all design specs.
**Purpose**: Ensures consistency across the entire project.

```markdown
# Style Guide

## Design Philosophy
[Brief statement about the visual approach]

## Target Audience
[Who this design serves]

## Color Palette

### Primary
- Main: #[hex] - [Usage: CTAs, key highlights]
- Light: #[hex] - [Usage: hover states]
- Dark: #[hex] - [Usage: pressed states]

### Neutral
- Background: #[hex]
- Surface: #[hex]
- Border: #[hex]
- Text Primary: #[hex]
- Text Secondary: #[hex]

### Accent
- Success: #[hex]
- Warning: #[hex]
- Error: #[hex]

### Do's and Don'ts
DO: [Guidance]
DON'T: [Anti-patterns]

## Typography

### Font Families
- Headlines: [Font name], [fallbacks]
- Body: [Font name], [fallbacks]
- Monospace: [Font name] (for code)

### Scale
- Display: [size]px / [line-height]
- H1: [size]px / [line-height]
- H2: [size]px / [line-height]
- H3: [size]px / [line-height]
- Body: [size]px / [line-height]
- Small: [size]px / [line-height]

## Spacing System
- xs: [value]
- sm: [value]
- md: [value]
- lg: [value]
- xl: [value]
- 2xl: [value]

## Border Radius
- sm: [value]
- md: [value]
- lg: [value]
- full: 9999px

## Shadows
[Shadow definitions]

## Animation
- Duration: [fast/medium/slow values]
- Easing: [easing functions]
- Motion Preferences: Respect prefers-reduced-motion

## Component Patterns
[Common patterns used across the site]

Important: This is a LIVING document. AI should update it as learnings emerge.


6. Project Requirements Document (PRD)

What: Technical specification for the entire project. Purpose: Tells AI exactly what tech to use and how.

markdown
# Project Requirements Document

## Project Overview
[Brief description]

## Tech Stack
- Framework: [Next.js / Remix / etc.]
- Styling: [Tailwind CSS / CSS Modules / etc.]
- UI Components: [shadcn/ui, Radix, etc.]
- Animation: [Framer Motion / GSAP / etc.]
- 3D: [Three.js / React Three Fiber]
- Icons: [Lucide / Heroicons / etc.]

## Dependencies
```json
{
  "dependencies": {
    // List all required packages
  }
}

File Structure

src/
├── app/
│   └── page.tsx
├── components/
│   ├── ui/           # shadcn components
│   ├── sections/     # Page sections
│   └── 3d/           # Three.js components
├── lib/
│   └── utils.ts
└── styles/
    └── globals.css

Design System

  • See: style-guide.md

Page Sections

SectionSpec FilePriority
Herohero-section.mdP0
Featuresfeatures-section.mdP1
[etc.][etc.][etc.]

Responsiveness

  • Mobile: 320px - 767px
  • Tablet: 768px - 1023px
  • Desktop: 1024px+

Performance Requirements

  • LCP: < 2.5s
  • FID: < 100ms
  • CLS: < 0.1

Accessibility

  • WCAG 2.1 AA compliance
  • Keyboard navigation
  • Screen reader support

---

### 7. Tasks Document
**What**: Step-by-step implementation plan.
**Purpose**: Gives AI a clear execution path.

```markdown
# Implementation Tasks

## Phase 1: Project Setup
- [ ] Initialize Next.js project
- [ ] Install dependencies
- [ ] Configure Tailwind CSS
- [ ] Set up shadcn/ui
- [ ] Create folder structure
- [ ] Configure fonts
- [ ] Set up color variables

## Phase 2: Core Components
- [ ] Build navigation bar
- [ ] Create button variants
- [ ] Set up typography components
- [ ] Create layout components

## Phase 3: Section Building
- [ ] Build Hero section
- [ ] Build Trust Logos section
- [ ] Build Features section
- [ ] [Continue for each section]

## Phase 4: Polish
- [ ] Add animations
- [ ] Optimize images
- [ ] Add loading states
- [ ] Mobile responsiveness pass
- [ ] Accessibility audit

## Phase 5: Launch
- [ ] Performance optimization
- [ ] SEO metadata
- [ ] Final review

Component Resources

shadcn/ui

The foundational component library. Copy-paste components with full customization.

21st.dev

Premium components built on top of shadcn/ui.

  • Website: https://21st.dev
  • Usage: Advanced components with animations
  • Key Feature: Each component includes:
    • Preview
    • Code to copy
    • AI prompt for installation

Three.js / React Three Fiber

3D graphics in the browser.

Sketchfab

Community 3D models and animations.


Best Practices

1. Section Isolation

Start a new chat for each section change:

  • Cleaner context (no pollution from other sections)
  • Cheaper (fewer tokens consumed)
  • More focused results

2. Commit Per Section

After each section is complete:

bash
git add .
git commit -m "feat(landing): add [section-name] section"

This allows easy rollback if iterations go wrong.

3. Include Reference Images

Always paste screenshots in your prompts:

  • AI can see exactly what you want
  • Reduces ambiguity
  • Faster convergence on the right design

4. Include Component Code

When specifying a component from 21st.dev or shadcn:

  • Copy the actual code
  • Include it in your section spec
  • AI can implement it exactly

5. Auto-Update Style Guide

Create a rule file:

markdown
# .cursorrules or similar

When building a section and making design decisions that differ from
the style guide, automatically update the style guide to reflect the
new learnings.

6. Screenshot-to-Iteration

When requesting changes:

  1. Take a screenshot of the current state
  2. Paste it in the prompt
  3. Describe what to change
  4. Reference the original inspiration if needed

The $500 vs $5000 Difference

Generic AI OutputPremium Framework Output
No contextFull context artifacts
Guessing what you wantFollowing precise specs
Inconsistent stylingLiving style guide
Random componentsCurated component library
No visual referencesMood boards + screenshots
Build everything at onceSection-by-section isolation
No iteration loopDefine → Build → Review → Refine

Prompt Templates

Generate Style Guide

Based on my mood board and design preferences in [website-sections folder]
and in the [product-brief.md], create a style guide that includes:
- Color palette (with usage guidance)
- Typography scale
- Component styles
- Spacing system
- Animation guidelines

This will be our single source of truth for the entire project.
Do not duplicate content from the section specs.

Generate PRD

Based on my [product-brief.md], [style-guide.md], and all section specs
in [website-sections], create a Project Requirements Document that includes:
- Project overview
- Tech stack (extract from component code in specs)
- Dependencies (extract from component libraries used)
- Design system reference
- Page sections with file references
- File structure
- Responsiveness requirements
- Performance requirements

Generate Tasks

Based on the [style-guide.md] and [prd.md], create a tasks markdown file with:
- Phase 1: Project setup tasks
- Phase 2: Core component tasks
- Phase 3: Section building tasks (one per section)
- Phase 4: Polish tasks
- Phase 5: Launch tasks

Each task should be a checkbox item.
Reference the specific spec files for each section.

Build a Section

Build the [Section Name] section.

Reference files:
- Style guide: @style-guide.md
- Section spec: @[section-name]-section.md
- PRD: @prd.md

Follow the design specs exactly.
Use the components specified.
Match the reference images.

Iterate on a Section

[Paste screenshot of current state]

Changes needed:
1. [Specific change 1]
2. [Specific change 2]

Reference the original inspiration: [paste reference image]

Attribution

This framework is derived from the video "How I Build Premium $5k SaaS Websites with AI" by BuilderSpace (December 2025), which documents a 10-year professional design workflow adapted for AI-assisted development.

Source: https://www.youtube.com/watch?v=WqSf0noa4hk


"The prep work feels like work. You just want to start building. But that upfront context - the brief, the mood boards, the style guide, the section specs - that's what separates a $500 generic website from a $5,000 premium polished one."

Frequently asked questions

What does the Premium Saas Design AI skill do?

Professional framework for building premium $5k+ SaaS websites with AI - the Define, Build, Review, Refine loop used by real product teams

Why use Premium Saas Design on TypingMind?

Because you install it once and use it with any model. Premium Saas Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Premium Saas Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/design-mastery/skills/premium-saas-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Premium Saas Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Premium Saas Design?

As many as you like. As long as a model supports skills, you can use Premium Saas Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Premium Saas Design AI skill free?

Yes. It is published on GitHub by HermeticOrmus under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇