Web Visual Direction logo

Web Visual Direction

Community
divyanshu-iitian
web-visual-direction

Define a distinctive, implementable visual direction for websites and web apps. Use when an agent must establish or repair art direction, typography, color, composition, imagery, density, motion, or the first-screen impression before substantial frontend implementation.

Overview

Publisherdivyanshu-iitian
Repositoryagent-website-design-skills
Skill nameweb-visual-direction
Stars
4
Forks
0
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by divyanshu-iitian on GitHub. Read the source before you install it.

Installation

Install the Web 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/divyanshu-iitian/agent-website-design-skills/tree/main/web-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/divyanshu-iitian/agent-website-design-skills.git /tmp/agent-website-design-skills
mkdir -p .claude/skills
cp -r /tmp/agent-website-design-skills/web-visual-direction .claude/skills/web-visual-direction
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Web 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 Web 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 Web 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.

Web Visual Direction

Turn an ambiguous brief into one coherent visual system. Make choices that fit the product and can survive implementation; do not produce a mood-board-shaped list of adjectives.

Workflow

  1. Inspect the product brief and existing code, brand assets, screenshots, content, component library, and constraints. Preserve intentional brand equity.
  2. State the audience, their immediate task, and the feeling the interface should create in one sentence each.
  3. Choose one visual thesis with a useful tension, such as "editorial authority with operational speed." Explain why it fits.
  4. Select two or three relevant references. Extract principles - rhythm, contrast, framing, density - not surface decoration or copyrighted layouts.
  5. Decide the composition before styling details:
    • identify the first viewport's focal point;
    • define the grid, content width, density, and section rhythm;
    • decide what intentionally breaks the grid, if anything.
  6. Define implementation-ready rules for typography, color, surfaces, borders, imagery, icons, and motion.
  7. Express the direction as a small token set and component implications. Reuse the project's existing styling system.
  8. Implement one representative viewport or component when implementation is in scope.
  9. Verify the direction at mobile and desktop widths. Remove choices that weaken comprehension, hierarchy, performance, or accessibility.

Decision Rules

  • Lead with the real product, work, place, person, object, or outcome.
  • Prefer a memorable structural idea over decorative effects.
  • Match density to the job: operational interfaces are compact; narrative brand pages can breathe.
  • Use typography with a reason. Do not ban or choose a font only because it is fashionable.
  • Use cards for meaningful grouping, not as the default container for every sentence.
  • Treat gradients, glass, grain, glow, and oversized type as tools, not proof of design quality.
  • Keep motion purposeful and respect reduced-motion preferences.
  • Do not fabricate brand assets, customer logos, metrics, or product screenshots.

Delivery Contract

Return or implement:

  1. Visual thesis - one sentence.
  2. Reference principles - what to borrow and what to avoid.
  3. Direction spec - composition, type, palette, surfaces, imagery, icons, and motion.
  4. Token sketch - named values or mappings compatible with the codebase.
  5. Responsive intent - what changes at narrow and wide widths.
  6. Proof - screenshot or inspected viewport when browser access exists.

Reference

Read references/site-archetypes.md when the product type should materially change the direction.

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 Web Visual Direction AI skill do?

Define a distinctive, implementable visual direction for websites and web apps. Use when an agent must establish or repair art direction, typography, color, composition, imagery, density, motion, or the first-screen impression before substantial frontend implementation.

Why use Web Visual Direction on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/divyanshu-iitian/agent-website-design-skills/tree/main/web-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 Web 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 Web Visual Direction?

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

Is the Web Visual Direction AI skill free?

Yes. It is published on GitHub by divyanshu-iitian 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 👇