Visual Direction logo

Visual Direction

Community
flitzrrr
visual-direction

Current visual direction for web projects covering color palettes, font pairings, layout compositions, and imagery (Q1/Q2 2026). Derived from Dribbble trending, Behance top projects, Land-book curation, and Godly featured sites. Structured for periodic updates.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill namevisual-direction
Stars
9
Forks
2
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Visual Direction 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.
    https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/visual-direction
  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/flitzrrr/frontend-design-skills.git /tmp/frontend-design-skills
mkdir -p .claude/skills
cp -r /tmp/frontend-design-skills/skills-src/visual-direction .claude/skills/visual-direction
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Visual Direction 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 Visual Direction 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 Visual Direction 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.

Visual-Direction

Current visual direction: color palettes, font pairings, layout compositions, and visual language (as of Q1/Q2 2026). Structured for periodic updates.

Scope

Use this skill when:

  • You are defining a color palette for a new project
  • You are selecting font pairings
  • You are planning layout compositions and visual rhythms
  • You are establishing a consistent visual language
  • You are implementing dark/light theming

Principles

1. Color Communicates Brand, Not Trend

Derive palettes from brand identity. Trends inform the framework; the brand determines the execution.

2. Typography Sets the Mood

Font choice defines the emotional tone more strongly than any other element. Grotesque = modern, serif = trust, display = creative.

3. White Space is Design

Empty space directs the eye, creates hierarchy, and signals premium quality.

4. Consistency Beats Creativity

A cohesive visual system looks more professional than sporadic brilliance.

5. Contrast Drives Hierarchy

Visual contrast (size, color, weight, space) is the primary tool for information hierarchy.

Rules

Color Palettes

  • DO: Define a structured palette with clear roles:
    • Primary: Brand color, used sparingly (CTAs, active states)
    • Neutral: Gray gradations (minimum 5 steps)
    • Semantic: Success (green), warning (yellow/orange), error (red), info (blue)
    • Accent: Optional, for highlights
  • DO: Deep darks for tech/SaaS: #0A0A0A to #1A1A1A (not #000000).
  • DO: Warm neutrals for lifestyle/brand: off-whites (#FAFAF5 to #F5F0EB).
  • DO: Monochrome accents -- one strong color is sufficient.
  • DON'T: More than 2 chromatic colors in the main palette.
  • DON'T: Saturated colors on large areas. High saturation only for small accents.
  • DON'T: Contrast ratio below 4.5:1 for text (WCAG AA).

Font Pairings

  • DO: Maximum 2 font families:
    • Option A: Geometric grotesque + humanist sans (e.g., Inter + DM Sans)
    • Option B: Modern serif + neutral sans (e.g., Fraunces + Inter)
    • Option C: Monospace + sans for developer tools (e.g., JetBrains Mono + Inter)
  • DO: Strong size contrast: display at least 3x larger than body (72-120px vs. 16-18px).
  • DO: Variable fonts where possible -- one file, many weights.
  • DON'T: Pair fonts with similar character. Contrast is essential.
  • DON'T: More than 4 weight levels per typeface.
  • DON'T: Body text below 16px.

Layout Composition

  • DO: Asymmetric balance -- not everything centered.
  • DO: Generous vertical rhythms: 120-200px section spacing on desktop.
  • DO: 12- or 16-column grid as a base, then break it deliberately.
  • DO: Full width for images, constrained (max 720px) for text (65-75 characters per line).
  • DON'T: Equal columns without variation. 50/50 splits appear static.
  • DON'T: More than 3 container widths per page.

Visual Language

  • DO: Consistent image treatment: same filters, perspective, style.
  • DO: 3D elements used selectively and subtly.
  • DO: Brand-specific illustrations (no generic libraries).
  • DO: Authentic photography with natural lighting.
  • DON'T: AI-generated images as primary visuals.
  • DON'T: Uncompressed images. WebP/AVIF with lazy loading.
  • DON'T: Images without alt text.

Palette archetypes and typography trends: see references/archetypen.md

Patterns

Dark Mode First

When: Tech products, developer tools, premium brands. What: Design starts with dark mode. Light mode is derived. CSS Custom Properties for theme switching.

Typographic Hero

When: Statement landing pages, agency sites, portfolios. What: No image, only typography. 100px+ headline, negative space as a design element.

Visual Rhythm Section

When: Long landing pages with multiple sections. What: Alternating background colors: dark > light > dark. Same palette, different temperature.

Monochrome + Accent

When: Minimalist products, luxury brands. What: Black-and-white/grayscale + a single accent color for CTAs and highlights.

Oversized Typography Grid

When: Portfolios, creative agencies, editorial. What: Large typography as a grid element. Letters break columns; text becomes a visual pattern.

Anti-Patterns

  1. Trend collage -- Glassmorphism + neubrutalism + neumorphism on one page. One style per project.
  2. Oversaturated gradients -- The purple-pink-orange of 2023 looks generic in 2026. Subtle monochrome gradients instead.
  3. Stock photo mix -- Images from different sources with inconsistent aesthetics.
  4. Font overload -- 4+ font families appear chaotic.
  5. Icon inconsistency -- Outlined + filled + duotone mixed. One style, one set.
  6. Shadow overkill -- Too many levels and directions. 3-5 levels suffice.
  7. Purely decorative elements -- Shapes without purpose. Every element must support hierarchy or mood.
  8. Contrast poverty -- Text on images without overlay. Use automated contrast checking.

Checklist

  • Color palette has defined roles: primary, neutral (5+ steps), semantic, accent
  • All text-background combinations meet WCAG AA (4.5:1)
  • Maximum 2 font families in the project
  • Body text at least 16px
  • Display text at least 3x larger than body
  • Section spacing consistent (e.g., 120px desktop, 64px mobile)
  • Images treated consistently (filter, perspective, style)
  • All images as WebP/AVIF with lazy loading
  • Icon set stylistically uniform
  • Shadow system maximum 5 levels
  • Dark mode implemented or used as primary theme
  • Color system uses CSS Custom Properties
  • No stock photos in hero or feature sections

Cross-References

  • design-trends -- Overarching trends shaping this visual direction
  • ui-patterns -- Patterns designed with this visual direction
  • component-patterns -- Token system for component theming
  • color-theory -- Color system fundamentals and token structure
  • web-typography -- Typography system and scaling
  • branding-identity -- Brand identity as the foundation of visual direction
  • images-media -- Image optimization and formats

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Visual Direction AI skill do?

Current visual direction for web projects covering color palettes, font pairings, layout compositions, and imagery (Q1/Q2 2026). Derived from Dribbble trending, Behance top projects, Land-book curation, and Godly featured sites. Structured for periodic updates.

Why use Visual Direction on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/visual-direction. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Visual Direction?

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 Visual Direction?

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

Is the Visual Direction AI skill free?

Yes. It is published on GitHub by flitzrrr 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 👇