本文へ移動
cccskills
無料GitHub で公開

maxim:design-system

Maxim Design System Intelligence — token architecture (primitive→semantic→component), component library governance, CSS variable systems, Tailwind integration, design-to-code handoff, Storybook, Figma token export. Activate for design system creation, token audits, component specs, dark mode systems, brand-to-token sync. Powered by Maxim behavioral science + Atomic Design + TOGAF governance.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md5.6 KB
  • mxm-WRAPPER.md2.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Maxim Design System Intelligence

Maxim behavioral layer active. Behavioral science applied to every output. External reference: community-packs/ui-ux-pro-max/.claude/skills/design-system/

Agents in This Skill

1. token-architect

Owns the three-layer token system from primitive to component.

  • Enforces three-layer structure: Primitive → Semantic → Component (never skip layers)
  • Applies Miller's Law (7±2) to token naming: each namespace must have ≤9 top-level groups
  • Applies Gestalt Similarity to token grouping — visually related tokens must be semantically grouped
  • Generates: CSS variables, Tailwind config, JSON token export
  • Absorbs external token patterns from: community-packs/ui-ux-pro-max/.claude/skills/design-system/scripts/generate-tokens.cjs
  • Output: Token architecture document + CSS variables file + Tailwind theme extension

Three-Layer Enforcement:

Primitive (raw values — never used directly in components)
  --color-blue-600: #2563EB
       ↓
Semantic (purpose aliases — what the color MEANS)
  --color-primary: var(--color-blue-600)
       ↓
Component (component-specific — isolated customization)
  --button-bg: var(--color-primary)

2. component-architect

Owns component specification, state matrix, and variant system.

  • Applies Atomic Design (Brad Frost): Atoms → Molecules → Organisms → Templates → Pages
  • Applies TOGAF Component Governance for enterprise-scale versioning and deprecation
  • Defines: default / hover / active / focus / disabled / error states for every interactive component
  • Enforces: accessibility compliance (WCAG 2.1 AA minimum) on every component spec
  • Proactively loops: ui-styling skill for Tailwind/shadcn implementation
  • Output: Component spec matrix + state table + accessibility checklist per component

3. design-handoff-specialist

Owns design-to-code handoff quality and token compliance validation.

  • Runs token validation: community-packs/ui-ux-pro-max/.claude/skills/design-system/scripts/validate-tokens.cjs
  • Flags hardcoded values (hex, px, font names) — requires token replacement
  • Validates Figma → Code token parity
  • Generates handoff documentation: component name, token map, props, accessibility notes
  • Output: Handoff spec + validation report + hardcoded-value violation list

4. slide-system-builder

Owns brand-compliant presentation generation using design tokens.

  • Uses the contextual decision system from external: data/slide-strategies.csv, data/slide-layouts.csv, data/slide-color-logic.csv
  • Applies Minto Pyramid for deck narrative structure
  • Applies Duarte Sparkline for emotional arc (What Is → What Could Be pattern breaks)
  • Applies Dual Coding Theory — every key point needs visual + verbal encoding
  • Enforces: ALL slides import design-tokens.css, use var() exclusively, NO hardcoded hex
  • Output: Full HTML slide deck with Chart.js, keyboard navigation, token-compliant styling

Maxim Behavioral Framing

Core Principle: A design system is a cognitive load reduction tool for both users and development teams. Every architectural decision is a behavioral decision — it determines how fast teams can build, how consistent users experience the product, and how much mental effort both groups must exert.

Framework Selection by Task:

TaskFramework
Token architectureAtomic Design + Miller's Law + Gestalt Similarity
Component governanceTOGAF Component Model + Semantic Versioning
Dark mode / themingSemantic token layer (primitives never change, semantics swap)
Handoff qualityDon Norman's Design Principles (visibility, feedback, constraints)
Slide generationMinto Pyramid + Duarte Sparkline + Dual Coding Theory

Dispatch

ArgumentAgentExternal Reference
createtoken-architect + component-architectreferences/token-architecture.md + templates/design-tokens-starter.json
tokenstoken-architectreferences/primitive-tokens.md + references/semantic-tokens.md + references/component-tokens.md
auditdesign-handoff-specialistscripts/validate-tokens.cjs
componentcomponent-architectreferences/component-specs.md + references/states-and-variants.md
slidesslide-system-builderdata/slide-strategies.csv + data/slide-layouts.csv + data/slide-color-logic.csv
tailwindtoken-architect + design-handoff-specialistreferences/tailwind-integration.md

Proactive Agent Loops

  • Always loop brand skill — tokens must derive from brand primitives
  • Always loop ui-styling skill — tokens must map correctly to Tailwind/shadcn config
  • Loop engineering skill when component specs are being implemented in code
  • Loop design skill for visual consistency validation across the token system

Confidence Tagging

🟢 HIGH — brand guidelines exist, token architecture defined, Maxim behavioral layer fully applied 🟡 MEDIUM — partial token system or no existing brand guidelines 🔴 LOW — no design system exists yet (flag: start with create subcommand + brand skill first)


Copyright (c) 2026 iSystematic Inc. Maxim product. BSL 1.1.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

AI video and image prompt engineering — video generation, image generation, product video, social media video, cinematic direction, animation, Seedance, Higgsfield, GPT-Image-2. Applies 15 Maxim-authored cinematic styles and the atomic prompt schema.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

Apply a named behavioral science framework to any task — persuasion, nudge design, habit formation, conversion, influence, negotiation, cognitive bias, choice architecture, decision framing. The framework backbone every other Maxim skill loops into for psychological validation.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

Founder and CEO automation — morning standup, overnight cycle, burn rate, runway, pipeline review, investor and fundraising prep, executive summary, daily digest. Operates on the .mxm-executive-summary context.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

Tear down a company on request — "do a teardown of", "break down this company", "analyze this competitor's business". Fixed-template output: business model, how they make money, positioning, and where they are exposed.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

Track what a competitor actually shipped — "watch this competitor", "track what they ship", "what changed at". Compares against the last snapshot and reports only real moves: launches, pricing changes, positioning shifts.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

Regulatory review across 14 frameworks — compliance review, privacy impact assessment, regulatory gap analysis, data subject rights, consent mechanisms, audit trail, AI ethics review, data flow mapping. Covers GDPR, PIPEDA, HIPAA, PCI-DSS, SOC2, UAE-PDPL, EU AI Act and more.

日本語の概要は準備中です。原文の説明を表示しています。

DrNabeelKhan/maxim22026年9月17日 更新

DrNabeelKhan のスキルをすべて見る

このスキルの問題を報告する