Design Info logo

Design Info

Community
arimaML
design-info

Corporate / info site lens. Use when the site's purpose is to explain and build trust — corporate sites, documentation, content-heavy sites, informational portals, blog hubs, public-sector sites. Load after design-core has established why the site exists and confirmed the goal is trust and clarity. Does not replace design-core; adds subtype-specific priorities, typical failures, and layer-by-layer guidance.

Overview

PublisherarimaML
Repositoryuniversal-design
Skill namedesign-info
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 Info 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-info
  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-info .claude/skills/design-info
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Info 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 Info 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 Info 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 Info — Corporate & Information Sites

A subtype lens for design-core. Load this after design-core has run its three entry steps and confirmed the goal is trust and clarity.

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 info sites.

Focus

Trust and structure. A lot of content, and it must be easy to find. Navigation is deep but never scary — the visitor should always know where they are and how to go back. Readability on long text is the primary craft. Design serves clarity; it does not perform.

Marketing does not run as a filter here — but a clear path to action (contact, sign-up, download) is part of the frame, not an afterthought.

Typical failures

  • Wall of text. Unbroken blocks with no hierarchy, no subheads, no air. Fix: break into sections, give every section one job, let space do the separating.
  • Five-level navigation. The menu nests deeper than the visitor will follow. Fix: no more than three levels; use search for depth.
  • No hierarchy inside sections. Every paragraph has the same weight, so nothing is skimmed. Fix: a real subhead system with visible hierarchy.
  • Buried dates or contacts. The two facts a visitor often needs first (what's current, how to reach you) are hidden. Fix: surface them.

Layer-by-layer

Frame (composition, space). The frame is a reading grid — 65–75 characters per line. Space separates sections, and section boundaries are felt, not just seen. Navigation is persistent and honest about current location. The composition serves comprehension; it does not try to impress.

Body (form, color). Color carries trust: restrained palettes, high contrast, no accent color used for decoration. Form is minimal — cards and containers serve grouping, not styling. Radius is small or absent; large radii read as playful and undermine authority.

Surface (texture, typography). Typography is the main tool. A clear type scale, readable body size, generous line height, and a real heading system. Texture is absent or near-absent; grain, gradient, and photographic ornament distract from reading.

Accent (point, line). Minimal. Dividers may be used to separate sections, but only if they carry structural meaning. Icons support navigation, not decoration. The accent color, if present, is reserved for links and calls to action.

Reading order

Info sites have two reading modes, and both matter:

  1. Scan — a visitor lands, understands what the site is, and finds their entry point in under 10 seconds. Hierarchy in headings, sections, and nav makes this possible.
  2. Read — a visitor settles on a page and reads long content. Line length, line height, contrast, and subheads make this bearable.

A page that serves only one of these modes fails the other.

Audit specifics

Beyond the common grid, these are the info-site breakages to hunt:

  • Space → Frame → navigation nests deeper than three levels → three levels max; search carries the depth.
  • Typography → Surface → paragraphs carry equal weight, nothing skimmable → a real subhead system with visible hierarchy.
  • Color → Body → accent used decoratively → accent is reserved for links and actions; trust reads from restraint.
  • Line → Accent → dividers between every section → rules only where boundaries carry structure.
  • Typography → Surface → dates and contacts buried at page end → the current/contact facts surface where visitors look first (in docs: TOC and search stay visible).

Return to core

For the method, see design-core/SKILL.md. For the words on long pages — headings, dates, links — see design-core/references/copy.md. For the layers protocol, see design-core/references/layers.md. For the audit grid — which is especially useful for large info sites — see design-core/references/audit-grid.md.

Frequently asked questions

What does the Design Info AI skill do?

Corporate / info site lens. Use when the site's purpose is to explain and build trust — corporate sites, documentation, content-heavy sites, informational portals, blog hubs, public-sector sites. Load after design-core has established why the site exists and confirmed the goal is trust and clarity. Does not replace design-core; adds subtype-specific priorities, typical failures, and layer-by-layer guidance.

Why use Design Info on TypingMind?

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

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

Which AI models can use Design Info?

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 Info?

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

Is the Design Info 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 👇