Brand Visual Generator logo

Brand Visual Generator

Community
kostja94
brand-visual-generator

When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user mentions "brand style guide," "visual identity," "design system," "typography," "color palette," "brand guidelines," "AI brand aesthetics," "brand colors," "font choices," "spacing system," "design tokens," "motion," "distinctive design," "frontend aesthetics," "PowerPoint theme," "Google Slides brand," or "slide master colors." For brand story, positioning, and voice, use branding.

Overview

Publisherkostja94
Repositorymarketing-skills
Skill namebrand-visual-generator
Stars
979
Forks
137
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 kostja94 on GitHub. Read the source before you install it.

Installation

Install the Brand Visual Generator 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/kostja94/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/components/branding/brand-visual .claude/skills/brand-visual-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Visual Generator 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 Brand Visual Generator 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 Brand Visual Generator 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.

Components: Brand Visual Identity

Guides visual identity for consistent brand presentation. Companies with consistent branding see up to 23-33% revenue lift; 94% of consumers say consistency influences buying decisions.

Keywords: visual identity, design tokens, color palette, typography, CSS variables, slide deck, brand guidelines, frontend aesthetics, accessibility

When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Initial Assessment

Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read Section 12 (Visual Identity) for colors, typography, spacing. See branding for brand strategy and visual identity strategy layer.

Identify:

  1. Scope: New brand, audit, or component design
  2. Touchpoints: Web, print, social, product UI, slides (PowerPoint, Google Slides, Keynote), documents (Word, Google Docs, PDF reports)
  3. Existing assets: Logo, style guide, design files

Best Practices

Typography

  • Two-font system: One display font for headlines, one body font for text. Contrast + harmony: different enough for distinct roles, similar enough to feel cohesive.
  • Body font: Prioritize legibility—large x-height, open counters. For neutral/safe: Source Sans 3, Lora, IBM Plex Sans. For distinctiveness: avoid overused AI fonts (Inter, Roboto, Arial, system fonts); prefer characterful choices that elevate the brand. See Frontend Aesthetics.
  • Headline font: Communicates brand voice; must be readable in under one second. Carries personality while body handles infrastructure.
  • Type scale: Use ratios 1.25–1.5 (Major Third or Perfect Fifth) for hierarchy. Limit to 3–4 styles per block.
  • Pairing rule: Decorative fonts only with neutral typefaces. Assign distinct roles; avoid mixing more than two families.
  • Sizes: Hero, section, subheading, body, caption; responsive scaling. Line length max 120 chars; generous line-height.

Color Palette

  • Structure: Primary, secondary, CTA, background, text. Use flexible systems (core hero color + complementary shades), not single rigid colors.
  • Industry mapping: Finance → blue, gray, navy (stability); Luxury → rose gold, burgundy, black (exclusivity); Tech → teal, neon accents, charcoal (innovation); Wellness → lavender, peach, mint (calm); Sustainability → sage green, earthy tones.
  • Reproduction: HEX, RGB, CMYK for print and digital. For programmatic slides (e.g. python-pptx), map brand HEX to RGB tuples (R, G, B) for fills and text; keep a single source of truth table (HEX + RGB) in the deliverable.
  • Accessibility: Contrast >=4.5:1 for normal text, >=3:1 for large text (18px+ or 14px+ bold). Don't rely on color alone for information.

Spacing

  • Margins: Horizontal (e.g. 120px), vertical section padding
  • Grid: Consistent spacing scale (8px base common)
  • Logo clear space: Minimum space around logo; document in brand guide

Logo Usage

  • Variants: Primary, secondary, monogram; light/dark backgrounds
  • Minimum size: Prevent illegibility
  • Don't: Stretch, recolor, add effects without approval

Anti-Patterns (Avoid)

  • Aesthetics over functionality: Don't sacrifice usability for visual appeal.
  • Unclear CTAs: Limit primary CTA to one per section; visually differentiate primary vs secondary.
  • Inconsistent elements: Pixelated icons, mismatched spacing/typography/color reduce trust.
  • Poor text hierarchy: Disordered, cluttered text confuses users.
  • Overusing effects: Drop shadows, pop-ups, crowded UI distract from content.
  • Chasing trends blindly: Adopt trends only when they fit project needs.
  • Ignoring performance: Heavy assets and complex layouts hurt load times.
  • Generic AI aesthetics: Inter, Roboto, Arial, Space Grotesk, and system fonts contribute to cookie-cutter design; avoid clichéd schemes (e.g., purple gradients on white). Prefer distinctive choices when brand differentiation matters.
  • Emoji as icons: Use SVG icons (Heroicons, Lucide, Simple Icons)—never emojis (🎨 🚀 ⚙️) as UI icons; emojis look unprofessional and inconsistent.
  • Unstable hover states: Use color/opacity transitions on hover; avoid scale transforms that shift layout or cause content jump.

Accessibility Checklist

  • Contrast: Normal text >=4.5:1; large text >=3:1; interactive elements >=3:1.
  • Focus: Visible focus indicator (>=2px solid, 3:1 contrast); logical Tab order; no keyboard traps.
  • Color: Never use color alone to convey information; add text or icons for states (error, success).
  • Keyboard: All interactive elements reachable via Tab, Enter, Spacebar.
  • Reduced motion: Respect prefers-reduced-motion for animations.

Frontend Aesthetics

Guides distinctive, production-grade frontend implementation. Components (hero, CTA, footer, etc.) and pages (landing, home, features) should reference these principles for visual differentiation. Intentionality over intensity: bold maximalism and refined minimalism both work when executed with precision.

Typography

  • Avoid generic AI fonts: Inter, Roboto, Arial, system fonts, Space Grotesk. These create cookie-cutter aesthetics.
  • Distinctive pairing: One display font (headlines, personality) + one refined body font (readability). Choose characterful, unexpected fonts that elevate the interface.
  • Consistency: Use CSS variables; limit to 3–4 type styles per block.

Motion

  • High-impact moments: One well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions.
  • Prioritize: CSS-only for HTML; Motion library for React when available. Scroll-triggering and hover states that surprise.
  • Accessibility: Always respect prefers-reduced-motion; provide reduced or no-motion alternatives.

Spatial Composition

  • Unexpected layouts: Asymmetry, overlap, diagonal flow, grid-breaking elements.
  • Balance: Generous negative space OR controlled density—choose intentionally.
  • Hierarchy: Clear visual flow; avoid predictable, evenly-distributed layouts.

Backgrounds & Visual Details

  • Atmosphere over flat: Create depth rather than defaulting to solid colors.
  • Techniques: Gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, grain overlays.
  • Context: Match effects to overall aesthetic; don't distract from content.

Never

  • Overused font families (Inter, Roboto, Arial, system fonts)
  • Clichéd color schemes (e.g., purple gradients on white)
  • Predictable layouts and cookie-cutter component patterns
  • Design that lacks context-specific character
  • Emojis as UI icons (use SVG: Heroicons, Lucide, Simple Icons)

AI Brand Aesthetics (Optional)

For AI/SaaS products, consider these visual trends and brand archetypes; adopt, ignore, or counter consciously to avoid sameness.

Visual Trends

TrendSignal
Off-white / beigeTrust, restraint, premium without gloss
Organic gradientsDistinctiveness; add grain, texture
Digital impressionismMood over literal; suggestive, not descriptive
Lomo / imperfectExploratory, human creativity
Contemporary realismPrecision, reliability, mastery
Sketch / scribbleHuman thought, exploration over certainty
Non-brand academiaAuthority; work speaks for itself
Technical illustrationsRigor, engineering depth
Quirky cutenessApproachability; counter doomsday narratives
Morphing objectsEmergence, systems that learn
Futuristic surrealismGateway to new worlds
Outer spaceExploration, unknown
ASCII / pixelsRetro, playful, technical
Generative artAlgorithmic, living system

Brand Archetypes

ArchetypeToneVisual
Likeable LeadersSeriousness, stability, trustMuted greys, warm beiges; impressionistic
Gentle HumanistsPeople before techHand-drawn, everyday moments, nature
Nerdy IdealistsEngineering cultureUnpolished, quirky, non-branded
Bold BuildersGroundbreaking, transformativeDark palettes, space references
Utopian DreamersWhat becomes possibleRetrofuturistic, surreal worlds

Product Marketing Context (Section 12)

When creating or updating .cursor/project-context.md, add:

markdown
## 12. Visual Identity (Optional)

**Colors**: Primary #XXX, secondary #XXX; backgrounds #XXX
**Typography**: Headings (font, weight, color); Body (font, weight, color)
**Sizes**: Hero Xpt, section Xpt, body Xpt
**Spacing**: Margins Xpx; section padding Xpx
**Layout**: Viewport, top bar, footer heights if fixed

Slides & Documents (Non-Web)

When the user asks for deck or document branding—not only websites:

  • Slide master: Background color from token; title font = display/heading token; body = body token; default title/body sizes aligned to type scale from branding / Section 12.
  • Theme colors: Map primary, secondary, background, text, and one accent to the presentation app's theme (PowerPoint Design → Variants, Google Slides Theme, Keynote Document settings) so shapes and charts inherit palette.
  • Charts & shapes: Cycle accents in a fixed order (e.g. primary → secondary → tertiary) instead of random colors; keeps decks on-brand.
  • Documents: Same fonts and heading hierarchy as web where possible; specify paragraph style names (Title, Heading 1–3, Normal) with point sizes and colors.

Strategy and narrative layers remain in branding; this section is visual execution for office/slide tools.

Brand Guidelines Structure (Single Source of Truth)

Ensure consistency across touchpoints. Include:

  • Logo: Usage rules, clear space, minimum sizes, variants (light/dark)
  • Colors: Primary, secondary, CTA, background, text (HEX, RGB, CMYK)
  • Typography: Font families, hierarchy, sizing, spacing
  • Imagery: Photography tone, subject matter, visual mood
  • Iconography: Style, stroke weight, usage rules

Output Format

  • Typography spec (fonts, weights, sizes, colors)
  • Color palette (HEX, usage rules, industry mapping)
  • Spacing scale
  • Logo clear space and variants
  • Frontend aesthetics (optional): Motion, spatial composition, backgrounds—for distinctive implementation
  • Anti-patterns and accessibility checklist
  • AI products (optional): Visual trend and archetype alignment
  • Context template for project-context Section 12
  • Slides/documents (when requested): theme mapping + master typography + chart accent order

Related Skills

  • branding: Brand strategy; visual identity strategy; this skill implements typography, colors, spacing
  • logo-generator: Logo placement, clear space; brand visual defines logo rules
  • favicon-generator: Favicon aligns with brand mark and colors
  • media-kit-page-generator: Media kit hosts brand guidelines document; links to logo, favicon
  • hero-generator: Hero uses brand typography, colors, spacing
  • 404-page-generator: Error pages maintain brand consistency

Frequently asked questions

What does the Brand Visual Generator AI skill do?

When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user mentions "brand style guide," "visual identity," "design system," "typography," "color palette," "brand guidelines," "AI brand aesthetics," "brand colors," "font choices," "spacing system," "design tokens," "motion," "distinctive design," "frontend aesthetics," "PowerPoint theme," "Google Slides brand," or "slide master colors." For brand story, positioning, and voice, use branding.

Why use Brand Visual Generator on TypingMind?

Because you install it once and use it with any model. Brand Visual Generator 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 Brand Visual Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kostja94/marketing-skills/tree/main/skills/components/branding/brand-visual. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Brand Visual Generator?

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 Brand Visual Generator?

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

Is the Brand Visual Generator AI skill free?

Yes. It is published on GitHub by kostja94 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 👇