Design System Research logo

Design System Research

Community
nnikochann
design-system-research

Use only to discover, audit, extract, normalize, or document a design system from existing product evidence when the system is missing, incomplete, stale, or undocumented. Trigger for requests to create/update design-system artifacts from an existing UI, component library, style files, Figma, website, screenshots, brand materials, or token/component audit. Do not use this skill just to design or implement UI from an already-created design system; in that case, read the existing docs/design-system artifacts directly and follow them.

Overview

Publishernnikochann
Repositorydesign-system-skills
Skill namedesign-system-research
Stars
3
Forks
0
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Design System Research 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/nnikochann/design-system-skills/tree/main/skills/design-system-research
  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/nnikochann/design-system-skills.git /tmp/design-system-skills
mkdir -p .claude/skills
cp -r /tmp/design-system-skills/skills/design-system-research .claude/skills/design-system-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design System Research 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 Research 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 Research 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 Research

Purpose

Build or repair compact, reusable design-system documentation from existing product evidence. A design system is the product contract between design intent and code: tokens, components, layout rules, interaction states, accessibility policy, content patterns, and governance. It is not just a palette or component library.

Use this skill when a product already has code, screens, Figma files, brand material, a public website, or prior UI decisions, but the design-system contract itself is absent, weak, outdated, or needs an audit. The job is to discover the system that exists and make it explicit.

This is not a UI-generation skill. If docs/design-system/manifest.json, docs/design-system/design-system.md, and docs/design-system/component-map.md already exist and the user asks to design a page, build a screen, update CSS, or implement a component, read those artifacts directly and proceed without invoking this skill unless the user asks to audit or revise the system itself.

Core Rule

Do not use this skill as a general preflight for every UI task. Use it only when design-system discovery or documentation is part of the work.

When this skill is active, do not start visual implementation until the current design system has been inspected and documented. If the user asks for implementation in the same run, complete the research artifacts first, then continue using them as constraints.

If there is no existing product, no existing UI, and the user wants a new visual system from references or a product idea, use $design-system-from-scratch instead.

If the design system already exists and the task is to create a screen from it, this skill is not applicable.

Workflow

  1. Inventory sources.

    • Inspect repo structure, frontend framework, routes/pages, component directories, style files, assets, and package dependencies.
    • Search for Tailwind config, theme files, CSS variables, CSS modules, global styles, design-token files, shadcn/Radix/MUI/Chakra usage, icons, fonts, and animation libraries.
    • If a Figma link is present and Figma MCP is available, pull design context, screenshot/context images, components, styles, and variable definitions. If the tool is unavailable, record that as a limitation instead of guessing.
    • If a website URL is present, capture key pages with browser or Playwright, then save screenshots under docs/design-system/screenshots/.
    • If screenshots, PPTX, PDFs, brand books, or moodboards are provided, treat them as design evidence and cite them in the manifest sources.
  2. Extract tokens.

    • Capture colors, typography, spacing, radius, shadows/elevation, breakpoints, grid, z-index/layers, motion timings/easing, and imagery rules.
    • Prefer semantic roles over raw values: surface, surface-muted, text-primary, accent, border-subtle, danger, focus-ring.
    • When a token is missing but repeatedly needed, propose it in manifest.json with a note. Do not silently hardcode new raw values.
  3. Map components.

    • Identify buttons, links, inputs, selects, checkboxes/toggles, cards, navigation, tabs, tables, dialogs, toasts, empty states, page shells, data visualizations, and marketing sections.
    • Record component paths, variants, supported states, composition rules, accessibility obligations, and local anti-patterns.
    • Reuse existing components before creating new ones. If an existing component is insufficient, explain the extension needed.
  4. Derive layout and visual language.

    • Document grid, page width, section rhythm, density, hierarchy, information architecture, responsive behavior, interaction patterns, motion style, icon style, illustration/photo rules, and content tone.
    • Name anti-patterns clearly: arbitrary gradients, nested decorative cards, floating glass panels, pill overload, fake dashboard widgets, unowned accent colors, inconsistent type scale, and layout drift.
  5. Write artifacts.

    • Read references/manifest-schema.md before writing manifest.json.
    • Create or update:
      • docs/design-system/manifest.json
      • docs/design-system/design-system.md
      • docs/design-system/component-map.md
    • Optional when useful:
      • docs/design-system/tokens.css
      • docs/design-system/visual-principles.md
      • docs/design-system/screenshots/
  6. Protect the project instructions.

    • After the design-system artifacts are written, search the repository root for an existing agent instruction file in this order: AGENTS.md, agents.md, AGENT.md, agent.md.
    • If one exists, update it. If none exists, create AGENTS.md at the repository root.
    • Add a short "Design System Guard" section explaining that the project's visual layer is protected by the design system: the design system is the source of truth for visual decisions, and UI work must follow it before introducing new styles, tokens, or components.
    • List the design-system files that own the contract. Include required files and any optional files that were actually created, for example:
      • docs/design-system/manifest.json
      • docs/design-system/design-system.md
      • docs/design-system/component-map.md
      • docs/design-system/tokens.css
      • docs/design-system/visual-principles.md
      • docs/design-system/screenshots/
    • Keep this instruction block concise. Do not duplicate the full design-system documentation inside the agent instruction file.
    • Use this shape, adapted to the project's language and actual file list:
      md
      ## Design System Guard
      
      The visual layer of this project is protected by the design system. The design system is the source of truth for UI decisions: colors, typography, spacing, components, layout, motion, and visual QA. Before changing UI, read and follow these files:
      
      - `docs/design-system/manifest.json`
      - `docs/design-system/design-system.md`
      - `docs/design-system/component-map.md`
      
      Do not introduce new visual tokens, component variants, or layout patterns unless they are added to the design-system contract first.
  7. Continue or stop.

    • If the user asked only for research, stop after the artifacts and summarize findings, open questions, and next recommended implementation step.
    • If the user asked for UI implementation too, proceed only after the artifacts exist. Treat the manifest as the source of truth.

Artifact Guidance

manifest.json is the machine-readable contract. Keep it compact, structured, and specific enough that another Codex run can implement from it.

design-system.md is the human-readable explanation. Explain what the system is, how to apply it, and where the strongest design decisions come from.

component-map.md is the engineering handoff. Link component names to file paths, variants, usage rules, states, and gaps.

The project agent instruction file (AGENTS.md, agents.md, AGENT.md, or agent.md) is the persistent guardrail. It should point future agents back to the design-system files and state that the design system is authoritative for visual work.

Verification

Before finishing a UI task that used this skill:

  • Run relevant lint, typecheck, tests, and build commands when available.
  • Render affected screens in browser or Playwright across mobile, tablet, and desktop when possible.
  • Check token usage, typography hierarchy, spacing rhythm, overflow, responsive states, focus states, contrast, and visual drift from manifest.json.
  • Confirm the project agent instruction file exists and references the design-system source-of-truth files.
  • Report verification commands, screenshots or capture paths, deviations, and remaining risks.

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 Research AI skill do?

Use only to discover, audit, extract, normalize, or document a design system from existing product evidence when the system is missing, incomplete, stale, or undocumented. Trigger for requests to create/update design-system artifacts from an existing UI, component library, style files, Figma, website, screenshots, brand materials, or token/component audit. Do not use this skill just to design or implement UI from an already-created design system; in that case, read the existing docs/design-system artifacts directly and follow them.

Why use Design System Research on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nnikochann/design-system-skills/tree/main/skills/design-system-research. 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 Research?

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 Research?

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

Is the Design System Research AI skill free?

Yes. It is published on GitHub by nnikochann 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 👇