Design System logo

Design System

Community
ymandrikov
design-system

Organise and maintain a consistent design system through contracts, discovery, reuse and verification. Handles locally added external components, design-only component and consumer changes, initial setup, adoption and migration, analysis, gaps and triage; component internals and business logic remain project-owned.

Overview

Publisherymandrikov
Repositoryai-design-system-demo-app
Skill namedesign-system
Stars
3
Forks
0
Bundled files
29
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.

  • 29 bundled files

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

  • Open source

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

Installation

Install the Design System 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/ymandrikov/ai-design-system-demo-app/tree/main/.agents/skills/design-system
  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/ymandrikov/ai-design-system-demo-app.git /tmp/ai-design-system-demo-app
mkdir -p .claude/skills
cp -r /tmp/ai-design-system-demo-app/.agents/skills/design-system .claude/skills/design-system
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design System 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 System 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 System 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 system

One entrypoint, two workflows with separate responsibilities. The framework governs design-system work and its checks; implementation and engineering test methods follow the project's procedures. Read the shared model once, then the procedure for the request. Load supporting references only when their stated condition applies. Within a project workflow, act as its design-system specialist under the shared responsibility boundary.

Choose the workflow

Accept explicit design-system craft <request> and design-system use <request>, or infer the workflow from the requested result. An explicit mode sets the scope; a missing capability does not expand it.

Requested resultRead and follow
Add external component sources to the project, or document a manual additioncraft external-component adoption in the same task
Survey and improve design-system consistency, including related consumer presentation while preserving logicimprove; read-only survey, then one choice to document or implement
Create or maintain components' design, layouts, patterns, contracts, tokens, rules or availability; fix a design-system gapcraft
Build or change a product interface by selecting and composing the system's public capabilitiesuse

craft delivers reusable system capabilities and evidence for their promises. use delivers a product interface and evidence for its composition and behaviour. A page request authorises product work and suitable local fallbacks; shared component development and system rule changes require craft scope. Record a reusable shortfall as a gap and hand it off to craft. Recording it does not authorise the repair.

An authorised external-component addition includes its bounded contract and index work through craft, even when another project skill owns installation. Direct library imports are outside this route; a page request alone does not authorise installing new components.

When both workflows are authorised, identify their separate stages and results. Follow craft → checks → use → checks: verify the shared capability before using it, then verify its actual composition, subject to explicit migration exceptions. Existing authorisation counts; crossing the boundary is not an automatic response to failed discovery. Keep unrelated system work outside the task.

Standalone procedures

Explicit design-system improve, analyze, setup, migrate, discovery, verify, gaps or triage, and equivalent natural language requests, reach the matching procedure directly. These are internal Markdown instructions, not additional skills. End at that procedure's result; standalone selection or review does not start implementation. Improve presents its survey before offering documentation or bounded system changes; its stricter scope remains in force when calling craft.

Request or workflow conditionRead and follow
Improve the existing system, or resume saved improvements, preserving logic and allowing scoped consumer design changesimprove; one read-only survey pass, then document or implement and verify
Analyze the codebase for component, layout or pattern extraction, consolidation or reuse candidatesanalyze; saved recommendations, with readiness determined by design-system artifacts and indexes
Select components, layouts, patterns or tokens; advise how to organise or adapt a composition; assess system coveragediscovery, read/search only; return the recommendation without writing files
Explicitly request project connection or its continuationsetup
Automatically migrate a connected project, or resume a saved automatic migrationmigrate; owns migration modes, batches and completion
Check an interface or component against its contracts and design sourcesverify
Record or assess a systemic shortfallgaps; resolving a system gap belongs to craft
Review open gaps, clean the journal or archive and recommend next worktriage; journal/archive maintenance and recommendations

Follow links by purpose

  • Read a rule: consult the named section when its condition applies; this does not execute its containing procedure. Reuse already-read unchanged rules.
  • Run a procedure: perform the named step within the caller's scope and return its result to that caller. A called section does not start the rest of its workflow.
  • Hand off work: return the result, missing inputs or required next stage. Execute that stage only under existing authority or a new authorised request.

Read-only discovery keeps its own scope when called by a writable workflow. Missing context and handoffs do not expand authority; useful calls with returns remain valid, without recursively restarting their callers.

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 System AI skill do?

Organise and maintain a consistent design system through contracts, discovery, reuse and verification. Handles locally added external components, design-only component and consumer changes, initial setup, adoption and migration, analysis, gaps and triage; component internals and business logic remain project-owned.

Why use Design System on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ymandrikov/ai-design-system-demo-app/tree/main/.agents/skills/design-system. 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 System?

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 System?

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

Is the Design System AI skill free?

Yes. It is published on GitHub by ymandrikov 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 👇