Design Thinking logo

Design Thinking

Community
connerkward
design-thinking

Direction and intent for frontend design. Use with design when defining purpose, tone, domain, color world, and review bar; includes cross-domain lens from cinema, architecture, marketing, UX, automotive, industrial design.

Overview

Publisherconnerkward
Repositoryckw-design-skill
Skill namedesign-thinking
Stars
9
Forks
1
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 connerkward on GitHub. Read the source before you install it.

Installation

Install the Design Thinking 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/connerkward/ckw-design-skill/tree/main/design-thinking
  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/connerkward/ckw-design-skill.git /tmp/ckw-design-skill
mkdir -p .claude/skills
cp -r /tmp/ckw-design-skill/design-thinking .claude/skills/design-thinking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Thinking 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 Thinking 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 Thinking 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 thinking

Apply with the design skill on every design task. Do this before coding.

Design thinking (before coding)

  • Purpose: What problem does this interface solve? Who uses it?
  • Tone: Pick an extreme and execute with intention — e.g. brutally minimal, maximalist, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian.
  • Constraints: Framework, performance, accessibility.
  • Differentiation: One thing that makes it unforgettable.

Commit to one bold direction. Intentionality over intensity.

Reserve impact for punctuation (use sparingly for effect)

High-impact devices — full-bleed media, dramatic motion, oversized type, a saturated accent, parallax — lose their force the moment they become the default. If every section is a full-screen video, none of them land. Choose 1–2 moments to go big (the hero, the payoff) and make everything else quiet and contained, so the big moments read as deliberate punctuation rather than noise. Restraint is what gives the rare full-bleed beat its hit; wall-to-wall intensity reads as flat. This is the luxury of reduction — a single bold gesture in generous negative space beats maximalism. Applies equally to scale, color (one accent, not five), and motion (one signature move, not constant animation).

Domain and color

  • Domain: 5+ concepts, metaphors, or vocabulary from the product's world (territory, not features).
  • Color world: 5+ colors that "belong" in that world — what you'd see if this product were a physical space. Not "warm" or "cool"; name actual colors from that domain.
  • Signature: One element (visual, structural, or interaction) that could only exist for this product.

Review bar

Ask: "Would I put my name on this?" Design-lead review means: not "does it work?" but "is this unmistakably intentional and crafted?"

Non-negotiable craft invariants (a single failure fails the review):

  • No font pop-in. Ever. Title/display text must never flash a fallback face or reflow as the webfont loads. Gate it on document.fonts.ready and fade in. See design-system → Never let fonts pop in.
  • First seen, first loaded. Whatever is in the opening viewport (hero text, hero media, brand mark) must be prioritized to paint complete and correct before anything below the fold loads. See design-system → Loading order.

Cross-domain lens

When defining direction, choose which disciplines fit the product and apply 2–3 principles from each. Examples: dashboard → UX + automotive; brand campaign → cinema + marketing; app → UX + industrial design.

Cinema

  • Framing and composition: Viewport as frame; rule of thirds, leading lines, foreground/mid/background depth. What's in focus = primary hierarchy.
  • Pacing and rhythm: Sequence of reveals (like editing). One well-orchestrated load or scroll beat beats scattered motion.
  • Color and mood: Color grading = mood; consistent palette as "look."
  • Focus and depth: Focal plane and depth of field → visual hierarchy and layering (blur, opacity, scale).

Architecture

  • Scale and proportion: Human scale, rhythm of columns/grid, proportion of elements to viewport.
  • Wayfinding: User always knows where they are and where they can go (orientation, nav, breadcrumbs).
  • Material and light: Texture and shadow create depth; light direction implies elevation and emphasis.
  • Negative space: Intentional emptiness; space as structure, not leftover.
  • Thresholds: Entrance and transition moments (landing → app, modal open) as deliberate "crossings."

Marketing

  • One hero message: Single value proposition or takeaway above the fold; hierarchy of message, not feature list.
  • Emotional vs rational: Decide whether the first beat is emotional pull or rational clarity; align layout and copy.
  • CTA prominence: Primary action unmistakable; secondary actions present but not competing.
  • Audience fit: Tone and imagery match who it's for; avoid "generic user."
  • Brand consistency: One coherent voice and visual system across the artifact.

UX

  • Goals and tasks: Design around user goals and key tasks; reduce steps to completion.
  • Information architecture: Clear grouping and hierarchy; cognitive load minimal.
  • Feedback and state: Every action has visible feedback; loading, success, error states considered.
  • Accessibility: Color contrast, focus order, semantics. (Reduced motion: honor prefers-reduced-motion for public/multi-user projects; personal projects may ship full motion.)
  • Progressive disclosure: Show essentials first; detail on demand (expand, modal, step).

Automotive (exterior / interior)

  • Silhouette and character: One strong silhouette or "character line"; recognizable at a glance.
  • Surface language: Tension, flow, continuity of surfaces (like body panels); avoid arbitrary bumps.
  • Proportion: Balance of "cab" (content) to "wheel" (chrome/nav); stable, not top-heavy.
  • Materials and trim: Hard/soft, cold/warm, matte/gloss as hierarchy; primary = one material language, accent = another.
  • Driver-centric layout: Primary controls and info where the "driver" (user) looks first; secondary in reach but not competing.
  • Control hierarchy: One primary action surface; secondary actions grouped and identifiable.

Industrial design

  • Form follows function: Shape and layout reflect use; no decoration without reason.
  • Material honesty: Materials (or visual equivalent: texture, weight) feel appropriate to the function.
  • Affordances: Shape suggests use (clickable, draggable, input); obvious without labels where possible.
  • Tactility: Buttons and controls feel "pressable" or "grabbable" (hover/active state, depth).
  • Product personality: One clear character (friendly, serious, playful, premium); consistent across the UI.
  • Simplify: Remove until it breaks; "best part is no part" for UI clutter.

Frequently asked questions

What does the Design Thinking AI skill do?

Direction and intent for frontend design. Use with design when defining purpose, tone, domain, color world, and review bar; includes cross-domain lens from cinema, architecture, marketing, UX, automotive, industrial design.

Why use Design Thinking on TypingMind?

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

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

Which AI models can use Design Thinking?

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 Thinking?

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

Is the Design Thinking AI skill free?

Yes. It is published on GitHub by connerkward 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 👇