Design Portfolio logo

Design Portfolio

Community
arimaML
design-portfolio

Portfolio / studio site lens. Use when the site's purpose is to impress through the work itself — designer, photographer, illustrator, agency, artist portfolios. Load after design-core has established why the site exists and confirmed the goal is impression, not conversion. Does not replace design-core; adds subtype-specific priorities, typical failures, and layer-by-layer guidance.

Overview

PublisherarimaML
Repositoryuniversal-design
Skill namedesign-portfolio
Stars
3
Forks
0
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 arimaML on GitHub. Read the source before you install it.

Installation

Install the Design Portfolio 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/arimaML/universal-design/tree/main/design-portfolio
  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/arimaML/universal-design.git /tmp/universal-design
mkdir -p .claude/skills
cp -r /tmp/universal-design/design-portfolio .claude/skills/design-portfolio
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Portfolio 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 Design Portfolio 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 Design Portfolio 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.

Design Portfolio — Portfolio & Studio Sites

A subtype lens for design-core. Load this after design-core has run its three entry steps and confirmed the goal is impression, not conversion.

This file does not redefine the eight elements, the four layers, the two modes, or the two phases. It only adds what is specific to portfolio sites.

Focus

The work is the center. Everything else is silence around it. Character matters more than conversion. The first screen is a statement, not a catalogue — it says what world the visitor has entered, not what's for sale. Navigation is subordinated to the work, not the reverse.

Design leads by default. Marketing is not active as a filter here, though a clear path to contact still matters.

Typical failures

  • Work drowns in decoration. Ornamental backgrounds, animated intros, parallax layers fighting the pieces. Fix: strip until the work is the loudest thing on the page.
  • Grid kills varied formats. A rigid grid imposes one aspect ratio on portraits, landscapes, and square pieces. Fix: let the grid flex per project, or use a masonry approach that respects each piece.
  • Animation for animation's sake. Every hover triggers a transition, every scroll triggers a fade. Fix: one orchestrated moment (page load or first reveal), motion that answers action otherwise.
  • No path to contact. Character without a way to reach you is a dead end. The contact path must be visible, not hidden in the footer.

Layer-by-layer

Frame (composition, space). The composition serves the work. Space is generous — the work needs air or it reads as an inventory. The first screen is a statement: a single image, a single line of type, or one crafted moment. The rest of the page holds the work in a rhythm, not in a grid.

Body (form, color). Color is restrained. The work provides the color — the site's palette should not compete with it. Form is soft where it needs to recede, sharp where it needs to frame. Radius is a decision, not a default.

Surface (texture, typography). Typography carries much of the character. The typeface is chosen, not defaulted — it is part of the site's voice. Type scale is deliberate; a portfolio can afford large display sizes because it has few words.

Accent (point, line). Minimal. Dividers and rules are used only if they encode structure. Icons, if present, are custom or drawn from a single coherent set. The accent never argues with the work.

Reading order

Portfolio reading order is about immersion, not conversion:

  1. Statement (first screen — what world is this)
  2. Work (the pieces, in a rhythm the visitor can move through)
  3. Contact (the path out)

Navigation may live at the side, in a persistent menu, or as a quiet top bar — but it never occupies more visual weight than the work itself.

Audit specifics

Beyond the common grid, these are the portfolio breakages to hunt:

  • Form → Body → the grid forces one aspect ratio on mixed work (portraits, landscapes, squares) → flex the grid per project, or use a masonry approach that respects each piece.
  • Color → Body → the site's palette competes with the work → the work provides the color; the site's palette recedes.
  • Typography → Surface → project descriptions set below readable body size → 16px floor and air, even over images.
  • Line → Accent → frames and rules around every piece add noise → borders only where they carry structure.
  • Space → Frame → no path to the next project ends the visit → each project points onward; contact is part of the frame.

Return to core

For the method, see design-core/SKILL.md. For the layers protocol, see design-core/references/layers.md. Marketing does not run as a filter here, but a path to contact is not optional — it is part of the frame.

Frequently asked questions

What does the Design Portfolio AI skill do?

Portfolio / studio site lens. Use when the site's purpose is to impress through the work itself — designer, photographer, illustrator, agency, artist portfolios. Load after design-core has established why the site exists and confirmed the goal is impression, not conversion. Does not replace design-core; adds subtype-specific priorities, typical failures, and layer-by-layer guidance.

Why use Design Portfolio on TypingMind?

Because you install it once and use it with any model. Design Portfolio 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 Design Portfolio in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/arimaML/universal-design/tree/main/design-portfolio. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Design Portfolio?

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 Design Portfolio?

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

Is the Design Portfolio AI skill free?

Yes. It is published on GitHub by arimaML 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 👇