Assembling Components logo

Assembling Components

Community
ancoleman
assembling-components

Assembles component outputs from AI Design Components skills into unified, production-ready component systems with validated token integration, proper import chains, and framework-specific scaffolding. Use as the capstone skill after running theming, layout, dashboard, data-viz, or feedback skills to wire components into working React/Next.js, Python, or Rust projects.

Overview

Publisherancoleman
Repositoryai-design-components
Skill nameassembling-components
Stars
523
Forks
73
Bundled files
11
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.

  • 11 bundled files

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

  • Open source

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

Installation

Install the Assembling Components 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.
  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/ancoleman/ai-design-components.git /tmp/ai-design-components
mkdir -p .claude/skills
cp -r /tmp/ai-design-components/skills/assembling-components .claude/skills/assembling-components
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Assembling Components 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 Assembling Components 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 Assembling Components 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.

Assembling Components

Purpose

This skill transforms the outputs of AI Design Components skills into production-ready applications. It provides library-specific context for our token system, component patterns, and skill chain workflow - knowledge that generic assembly patterns cannot provide. The skill validates token integration, generates proper scaffolding, and wires components together correctly.

When to Use

Activate this skill when:

  • Completing a skill chain workflow (theming → layout → dashboards → data-viz → feedback)
  • Generating new project scaffolding for React/Vite, Next.js, FastAPI, Flask, or Rust/Axum
  • Validating that all generated CSS uses design tokens (not hardcoded values)
  • Creating barrel exports and wiring component imports correctly
  • Assembling components from multiple skills into a unified application
  • Debugging integration issues (missing entry points, broken imports, theme not switching)
  • Preparing generated code for production deployment

Skill Chain Context

This skill understands the output of every AI Design Components skill:

┌──────────────────┐     ┌──────────────────┐     ┌──────────────────┐
│ theming-         │────▶│ designing-       │────▶│ creating-        │
│ components       │     │ layouts          │     │ dashboards       │
└──────────────────┘     └──────────────────┘     └──────────────────┘
        │                        │                        │
        ▼                        ▼                        ▼
    tokens.css               Layout.tsx             Dashboard.tsx
    theme-provider.tsx       Header.tsx             KPICard.tsx
        │                        │                        │
        └────────────────────────┴────────────────────────┘
                    ┌──────────────────────┐
                    │ visualizing-data     │
                    │ providing-feedback   │
                    └──────────────────────┘
                         DonutChart.tsx
                         Toast.tsx, Spinner.tsx
                    ┌──────────────────────┐
                    │ ASSEMBLING-          │
                    │ COMPONENTS           │
                    │ (THIS SKILL)         │
                    └──────────────────────┘
                       WORKING COMPONENT SYSTEM

Expected Outputs by Skill

SkillPrimary OutputsToken Dependencies
theming-componentstokens.css, theme-provider.tsxFoundation
designing-layoutsLayout.tsx, Header.tsx, Sidebar.tsx--spacing-, --color-border-
creating-dashboardsDashboard.tsx, KPICard.tsxAll layout + chart tokens
visualizing-dataChart components, legends--chart-color-, --font-size-
building-formsForm inputs, validation--spacing-, --radius-, --color-error
building-tablesTable, pagination--color-, --spacing-
providing-feedbackToast, Spinner, EmptyState--color-success/error/warning

Token Validation

Run Validation Script (Token-Free Execution)

bash
# Basic validation
python scripts/validate_tokens.py src/styles

# Strict mode with fix suggestions
python scripts/validate_tokens.py src --strict --fix-suggestions

# JSON output for CI/CD
python scripts/validate_tokens.py src --json

Our Token Naming Conventions

css
/* Colors - semantic naming */
--color-primary: #FA582D;          /* Brand primary */
--color-success: #00CC66;          /* Positive states */
--color-warning: #FFCB06;          /* Caution states */
--color-error: #C84727;            /* Error states */
--color-info: #00C0E8;             /* Informational */

--color-bg-primary: #FFFFFF;       /* Main background */
--color-bg-secondary: #F8FAFC;     /* Elevated surfaces */
--color-text-primary: #1E293B;     /* Body text */
--color-text-secondary: #64748B;   /* Muted text */

/* Spacing - 4px base unit */
--spacing-xs: 0.25rem;   /* 4px */
--spacing-sm: 0.5rem;    /* 8px */
--spacing-md: 1rem;      /* 16px */
--spacing-lg: 1.5rem;    /* 24px */
--spacing-xl: 2rem;      /* 32px */

/* Typography */
--font-size-xs: 0.75rem;   /* 12px */
--font-size-sm: 0.875rem;  /* 14px */
--font-size-base: 1rem;    /* 16px */
--font-size-lg: 1.125rem;  /* 18px */

/* Component sizes */
--icon-size-sm: 1rem;      /* 16px */
--icon-size-md: 1.5rem;    /* 24px */
--radius-sm: 4px;
--radius-md: 8px;
--shadow-sm: 0 1px 2px rgba(0,0,0,0.05);

Validation Rules

Must Use Tokens (Errors)Example Fix
Colors#FA582Dvar(--color-primary)
Spacing (≥4px)16pxvar(--spacing-md)
Font sizes14pxvar(--font-size-sm)
Should Use Tokens (Warnings)Example Fix
Border radius8pxvar(--radius-md)
Shadows0 4px...var(--shadow-md)
Z-index (≥100)1000var(--z-dropdown)

Framework Selection

React/TypeScript

Choose Vite + React when:

  • Building single-page applications
  • Lightweight, fast development builds
  • Maximum control over configuration
  • No server-side rendering needed

Choose Next.js 14/15 when:

  • Need server-side rendering or static generation
  • Building full-stack with API routes
  • SEO is important
  • Using React Server Components

Python

Choose FastAPI when:

  • Building modern async APIs
  • Need automatic OpenAPI documentation
  • High performance is required
  • Using Pydantic for validation

Choose Flask when:

  • Simpler, more flexible setup
  • Familiar with Flask ecosystem
  • Template rendering (Jinja2)
  • Smaller applications

Rust

Choose Axum when:

  • Modern tower-based architecture
  • Type-safe extractors
  • Async-first design
  • Growing ecosystem

Choose Actix Web when:

  • Maximum performance required
  • Actor model benefits your use case
  • More mature ecosystem

Implementation Approach

1. Validate Token Integration

Before assembly, check all CSS uses tokens:

bash
python scripts/validate_tokens.py <component-directory>

Fix any violations before proceeding.

2. Generate Project Scaffolding

React/Vite:

tsx
// src/main.tsx - Entry point
import { StrictMode } from 'react'
import { createRoot } from 'react-dom/client'
import { ThemeProvider } from '@/context/theme-provider'
import App from './App'
import './styles/tokens.css'   // FIRST - token definitions
import './styles/globals.css'  // SECOND - global resets

createRoot(document.getElementById('root')!).render(
  <StrictMode>
    <ThemeProvider>
      <App />
    </ThemeProvider>
  </StrictMode>,
)

index.html:

html
<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>{{PROJECT_TITLE}}</title>
  </head>
  <body>
    <div id="root"></div>
    <script type="module" src="/src/main.tsx"></script>
  </body>
</html>

3. Wire Components Together

Theme Provider:

tsx
// src/context/theme-provider.tsx
import { createContext, useContext, useEffect, useState } from 'react'

type Theme = 'light' | 'dark' | 'system'

const ThemeContext = createContext<{
  theme: Theme
  setTheme: (theme: Theme) => void
} | undefined>(undefined)

export function ThemeProvider({ children }: { children: React.ReactNode }) {
  const [theme, setTheme] = useState<Theme>('system')

  useEffect(() => {
    const root = document.documentElement
    const systemTheme = window.matchMedia('(prefers-color-scheme: dark)').matches
      ? 'dark' : 'light'
    root.setAttribute('data-theme', theme === 'system' ? systemTheme : theme)
    localStorage.setItem('theme', theme)
  }, [theme])

  return (
    <ThemeContext.Provider value={{ theme, setTheme }}>
      {children}
    </ThemeContext.Provider>
  )
}

export const useTheme = () => {
  const context = useContext(ThemeContext)
  if (!context) throw new Error('useTheme must be used within ThemeProvider')
  return context
}

Barrel Exports:

tsx
// src/components/ui/index.ts
export { Button } from './button'
export { Card } from './card'

// src/components/features/dashboard/index.ts
export { KPICard } from './kpi-card'
export { DonutChart } from './donut-chart'
export { Dashboard } from './dashboard'

4. Configure Build System

vite.config.ts:

typescript
import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
import path from 'path'

export default defineConfig({
  plugins: [react()],
  resolve: {
    alias: {
      '@': path.resolve(__dirname, './src'),
    },
  },
})

tsconfig.json:

json
{
  "compilerOptions": {
    "target": "ES2020",
    "lib": ["ES2020", "DOM", "DOM.Iterable"],
    "module": "ESNext",
    "moduleResolution": "bundler",
    "jsx": "react-jsx",
    "strict": true,
    "baseUrl": ".",
    "paths": { "@/*": ["./src/*"] }
  },
  "include": ["src"]
}

Cross-Skill Integration

Using Theming Components

tsx
// Import tokens first, components inherit token values
import './styles/tokens.css'

// Use ThemeProvider at root
<ThemeProvider>
  <App />
</ThemeProvider>

Using Dashboard Components

tsx
// Components from creating-dashboards skill
import { Dashboard, KPICard } from '@/components/features/dashboard'

// Wire with data
<Dashboard>
  <KPICard
    label="Total Threats"
    value={1234}
    severity="critical"
    trend={{ value: 15.3, direction: 'up' }}
  />
</Dashboard>

Using Data Visualization

tsx
// Charts from visualizing-data skill
import { DonutChart } from '@/components/charts'

// Charts use --chart-color-* tokens automatically
<DonutChart
  data={threatData}
  title="Threats by Severity"
/>

Using Feedback Components

tsx
// From providing-feedback skill
import { Toast, Spinner, EmptyState } from '@/components/feedback'

// Wire toast notifications
<ToastProvider>
  <App />
</ToastProvider>

// Use spinner for loading states
{isLoading ? <Spinner /> : <Dashboard />}

Integration Checklist

Before delivery, verify:

  • Token file exists (tokens.css) with all 7 categories
  • Token import order correct (tokens.css → globals.css → components)
  • No hardcoded values (run validate_tokens.py)
  • Theme toggle works (data-theme attribute switches)
  • Reduced motion supported (@media (prefers-reduced-motion))
  • Build completes without errors
  • Types pass (TypeScript compiles)
  • Imports resolve (no missing modules)
  • Barrel exports exist for each component directory

Bundled Resources

Scripts (Token-Free Execution)

  • scripts/validate_tokens.py - Validate CSS uses design tokens
  • scripts/generate_scaffold.py - Generate project boilerplate
  • scripts/check_imports.py - Validate import chains
  • scripts/generate_exports.py - Create barrel export files

Run scripts directly without loading into context:

bash
python scripts/validate_tokens.py demo/examples --fix-suggestions

References (Detailed Patterns)

  • references/library-context.md - AI Design Components library awareness
  • references/react-vite-template.md - Full Vite + React setup
  • references/nextjs-template.md - Next.js 14/15 patterns
  • references/python-fastapi-template.md - FastAPI project structure
  • references/rust-axum-template.md - Rust/Axum project structure
  • references/token-validation-rules.md - Complete validation rules

Examples (Complete Implementations)

  • examples/react-dashboard/ - Full Vite + React dashboard
  • examples/nextjs-dashboard/ - Next.js App Router dashboard
  • examples/fastapi-dashboard/ - Python FastAPI dashboard
  • examples/rust-axum-dashboard/ - Rust Axum dashboard

Assets (Templates)

  • assets/templates/react/ - React project templates
  • assets/templates/python/ - Python project templates
  • assets/templates/rust/ - Rust project templates

Application Assembly Workflow

  1. Validate Components: Run validate_tokens.py on all generated CSS
  2. Choose Framework: React/Vite, Next.js, FastAPI, or Rust based on requirements
  3. Generate Scaffolding: Create project structure and configuration
  4. Wire Imports: Set up entry point, import chain, barrel exports
  5. Add Providers: ThemeProvider, ToastProvider at root
  6. Connect Components: Import and compose feature components
  7. Configure Build: vite.config, tsconfig, package.json
  8. Final Validation: Build, type-check, lint
  9. Document: README with setup and usage instructions

For library-specific patterns and complete context, see references/library-context.md.

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 Assembling Components AI skill do?

Assembles component outputs from AI Design Components skills into unified, production-ready component systems with validated token integration, proper import chains, and framework-specific scaffolding. Use as the capstone skill after running theming, layout, dashboard, data-viz, or feedback skills to wire components into working React/Next.js, Python, or Rust projects.

Why use Assembling Components on TypingMind?

Because you install it once and use it with any model. Assembling Components 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 Assembling Components in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ancoleman/ai-design-components/tree/main/skills/assembling-components. 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 Assembling Components?

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 Assembling Components?

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

Is the Assembling Components AI skill free?

Yes. It is published on GitHub by ancoleman 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 👇