Design Skill logo

Design Skill

Community
TudeOrangBiasa
design-skill

Frontend design partner. Kills AI-slop by teaching 10 tells with positive direction. Five commands: detect, audit, deslop, shape, craft. Model-invoked: flag tells, run detect. User-invoked: grill first.

Overview

PublisherTudeOrangBiasa
Repositorydesign-skill
Skill namedesign-skill
Stars
9
Forks
1
Bundled files
56
LicenseApache-2.0
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.

  • 56 bundled files

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

  • Open source

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

Installation

Install the Design Skill 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/TudeOrangBiasa/design-skill/tree/master
  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/TudeOrangBiasa/design-skill.git \
  .claude/skills/design-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Skill 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 Skill 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 Skill 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.

The 10 Tells

TellWhy machine-madeDo instead
Tech gradientpurple-violet gloss signals nothingone real color story, flat/subtle
Generic tech hueindigo "because software"choose hue with reason; refuse category defaults
Feature-tile grid3 equal cards, no hierarchyasymmetry: one clearly primary
Accent railstripe posing as organizationreal grouping + spacing, not paint
Unearned blurglass as a "modern" signalblur only when it serves legibility
Stat monumentinvented 10k+/99.9%/24-7 rowsreal numbers or specific claims
Icon toppericon tile above every headinglead with the word; icons only for scanning
Template herocentered hero stack, 100vhbreak the spine: offset grid, strong edge
Default type stackInter everywhere, flat 700 headingseditorial contrast; ≥1.25x; 60-76ch
Anti-reference echodesign guessable from a banned listrestart with a direction contract: register+mode+scene

Invocation

Model-invoked: UI in view → flag tells, offer the command; HTML reachable → run detect. User-invoked: shape/craft grill first; audit/deslop take a target.

Commands

Abilities are flags, never standalone.

  • detect <target> - run detector.mjs, report tells
  • audit [--a11y|--responsive|--interaction|--checkup|--polish] - two-axis scored report; findings carry severity, element, fix; Spec axis quotes the brief
  • deslop [--distill|--bolder|--quieter|--harden] - kill tells with positive alternatives; every fix replaces with a rationale, never bare removal
  • shape - grill in frontier rounds, every question with a recommendation; settle register/mode/persona → brief
  • craft [--typeset|--colorize|--layout|--animate|--document] - brief-confirmed build; --document writes DESIGN.md (design.md)

Build doctrine

  • Layout: name the structure in one sentence before markup (asymmetric split, strict grid, editorial column, dense shell); never the centered stack; no KPI-monument hero (big figure + small label + stat row) - lead with the delta or a table. Sections differ in rhythm; one focal point per viewport (Hick's, Fitts, Von Restorff).
  • Story: Persuade pages follow six beats: Hook, Catalyst, Mentor, Journey, Proof, Resolution (shape.md). Proof names a real person + result - never invent, never omit. One primary CTA; every button leads to it, in-page anchors included.
  • Motion: one primary moment per surface, custom easing, transform/opacity - never width/height.
  • Numbers: replace invented stats, testimonials, or attributions (10k+, "Dan W. since 2023") with real, checkable claims - a fake figure is a tell, not content.
  • Modals: complex multi-section settings live on their own page, never in a modal.
  • Register-fit: ops UI stays dense and scannable - no serif greeting, cream, tracked-caps kickers, or magazine copy, even if the source theme is editorial.
  • Icons: one real set (Lucide, Phosphor, Tabler, Iconoir, Humbleicons, Flowbite); fetch it, no hand-drawn mascots, no emoji.
  • Imagery: image-led briefs ship real/generated imagery, URLs verified; colored div = bug.
  • Color: generate palettes in OKLCH: one hue with a reason, equal-L steps, same C% across hues, accent from a different hue; hex/hsl only where the framework needs it. Never category-reflex (coffee -> brown, cozy -> beige, tech -> indigo).
  • Font: pick as a physical object (museum caption, terminal manual); reject reflex defaults (Inter, Fraunces, Space Grotesk).
  • Reference hunt: web-search 2-3 inspirations that fit the brief (layout, type, palette); cite them.

Modes & register

Register: brand or product (register.md). Mode: Persuade/Operate/Read/Experience, from the surface.

Setup

Load context (node scripts/load-context.mjs; PRODUCT.md/DESIGN.md/brief.md optional, never block). Read modes.md + register.md. Load REFERENCE.md when invoked.

Truthful completion

Verify each change in real files before claiming done; bounded passes.

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 Design Skill AI skill do?

Frontend design partner. Kills AI-slop by teaching 10 tells with positive direction. Five commands: detect, audit, deslop, shape, craft. Model-invoked: flag tells, run detect. User-invoked: grill first.

Why use Design Skill on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TudeOrangBiasa/design-skill/tree/master. 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 Design Skill?

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 Skill?

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

Is the Design Skill AI skill free?

Yes. It is published on GitHub by TudeOrangBiasa under the Apache-2.0 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 👇