design-system
Generate or audit a design system from Tailwind or CSS tokens, extract and check design tokens, run an AI-slop visual-consistency audit, and review…
Skill by jeanchastel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jeanchastel-design-system
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/design-system
What's inside
- Skill name
design-system- Description
- Generate or audit a design system from Tailwind or CSS tokens, extract and check design tokens, run an AI-slop visual-consistency audit, and review styling-only PRs. Use for token and styling-system work, not general UX critique; defer UX critique to the design plugin.
- License
- MIT
- Instructions
- 110 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- design-md-schema.md · references/
SKILL.md (first lines)
# Design System: Generate & Audit Visual Systems ## When to Use - Starting a new project that needs a design system - Auditing an existing codebase for visual consistency - Before a redesign: understand what you have - When the UI looks "off" but you can't pinpoint why - Reviewing PRs that touch styling ## Artifact contract Reads `DESIGN.md` in audit mode or the project codebase in generate mode. Writes `DESIGN.md` against the nine-section schema (`references/design-md-schema.md`). Consumed by review-pass and the audit workflows. See `docs/document-contract.md`. ## How It Works ### Mode 1: Generate Design System Analyzes your codebase and generates a cohesive design system: ```text 1. Scan CSS/Tailwind/styled-components for existing patterns 2. Extract: colors, typography, spacing, border-radius, shadows, breakpoints 3. Research 3 competitor sites for inspiration (via browser MCP) 4. Propose a design token set (JSON + CSS custom properties) 5. Generate DESIGN.md against the 9-section schema, with rationale per decision 6. Create an interactive HTML preview page (self-contained, no deps) ``` Output: `DESIGN.md` + `design-tokens.json` + `design-preview.html` `DESIGN.md` follows the nine-section schema in `references/design-md-schema.md` (Brand & Personality, Color System, Typography, Spacing & Layout, Elevation & Surfaces, Motion & Interaction, Components, Accessibility, Implementation & Tokens). Emit every section in order; never leave a placeholder: if a decision is unmade, state the default chosen and why. The schema's closing contract holds: a brand or theme change is a token change in section 9, not a component edit. Image intake (optional source). Instead of or alongside the codebase scan in step 1, derive tokens from a provided image: a screenshot, mockup, or exported artboard. Use vision to read the color palette, the typography hierarchy, the spacing scale, and the radius and shadow treatment, then feed the same token set and DESIGN.md schema as above. This needs a vision-capable model. Extraction is approximate, so confirm the derived tokens with the operator before writing them. The Figma-URL path is deferred and out of scope here, because it needs external Figma access. ### Mode 2: Visual Audit Scores your UI across 10 dimensions (0-10 each): ```text 1. Color consistency: are you using your palette or random hex values? 2. Typography hierarchy: clear h1 > h2 > h3 > body > caption? 3. Spacing rhythm: consistent scale (4px/8px/16px) or arbitrary? 4. Component consistency: do similar elements look similar? 5. Responsive behavior: fluid or broken at breakpoints? 6. Dark mode: complete or half-done? 7. Animation: purposeful or gratuitous? 8. Accessibility: contrast ratios, focus states, touch targets 9. Information density: cluttered or clean? 10. Polish: hover states, transitions, loading states, empty states ``` Each dimension gets a score, specific examples, and a fix with exact file:line. Map findings back to the `references/design-md-schema.md` section they belong to (e.g. color drift → section 2, arbitrary spacing → section 4) so an audit reads as gaps against the documented system, not a loose list. ### Mode 3: AI Slop Detection Identifies generic AI-generated design patterns: ```text - Gratuitous gradients on everything - Purple-to-blue defaults - "Glass morphism" cards with no purpose - Rounded corners on things that shouldn't be rounded - Excessive animations on scroll - Generic hero with centered text over stock gradient - Sans-serif font stack with no personality - Cream or off-white backgrounds - Italic accent words in headlines - Numbered "01/02/03" section labels - Monospace labels - Pill-shaped buttons ``` ## Examples **Generate for a SaaS app:** ```text /design-system generate --style minimal --palette earth-tones ``` **Audit existing UI:** ```text /design-system audit --url http://localhost:3000 --pages / /pricing /docs ``` **Check for AI slop:** ```text /design-system slop-check ```
From jeanchastel/arkira, MIT.
More from jeanchastel/arkira
- 0.570score
onboarding
jeanchastel
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
SkillAFreshness: AClaude Code +9 - 0.570score
click-audit
jeanchastel
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out…
SkillAFreshness: AClaude Code +9 - 0.570score
intent-layer
jeanchastel
Scaffold or audit a repo's hierarchical AGENTS.md Intent Layer.
SkillAFreshness: AClaude Code +9 - 0.570score
intake-runbook
jeanchastel
Take a client's externally-hosted project (Lovable export, a repo on another GitHub/GitLab, a dev project) and re-home it onto your own GitHub + Vercel, then…
SkillAFreshness: AClaude Code +9 - 0.565score
deploy-prep
jeanchastel
Pre-flight gate before pushing a static brochure site to FTP or Netlify, composing html-audit, a11y-audit-aa, perf-budget, responsive, and deploy-specific…
SkillAFreshness: AClaude Code +9 - 0.565score
adr
jeanchastel
Capture architectural decisions made during Claude Code sessions as structured ADRs with context, alternatives considered, rationale, and an ADR log.
SkillAFreshness: AClaude Code +9 - 0.565score
bug-report
jeanchastel
Use when behavior looks like an Arkira harness defect in any repo, including bin/arkira, goal, gate, session state, hooks, or Arkira CI workflows.
SkillAFreshness: AClaude Code +9 - 0.565score
context-discipline
jeanchastel
Use when a task involves heavy file reading, repo-wide search, or long tool output.
SkillAFreshness: AClaude Code +9 - 0.565score
css-tokens
jeanchastel
Migrate hardcoded color, spacing, and typography values in static-site CSS to custom properties aligned with the static-web token layer and entity brand kit.
SkillAFreshness: AClaude Code +9 - 0.565score
perf-budget
jeanchastel
Check a static brochure site against the static-web performance budget: Lighthouse mobile 90+, page weight under 1MB, WebP with srcset, self-hosted fonts with…
SkillAFreshness: AClaude Code +9 - 0.561score
ideate
jeanchastel
Mine an operator's business or expertise to score three to five product directions and sharpen one into docs/product-idea.md.
SkillAFreshness: AClaude Code +9 - 0.561score
native-scaffold
jeanchastel
Scaffold an Expo + React Native native app version of an existing Arkira web app with shared design tokens and EAS.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jeanchastel/arkira
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jeanchastel
- 0.570score
intent-layer
jeanchastel
Scaffold or audit a repo's hierarchical AGENTS.md Intent Layer.
SkillAFreshness: AClaude Code +9 - 0.570score
onboarding
jeanchastel
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
SkillAFreshness: AClaude Code +9 - 0.570score
click-audit
jeanchastel
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out…
SkillAFreshness: AClaude Code +9 - 0.570score
intake-runbook
jeanchastel
Take a client's externally-hosted project (Lovable export, a repo on another GitHub/GitLab, a dev project) and re-home it onto your own GitHub + Vercel, then…
SkillAFreshness: AClaude Code +9 - 0.565score
context-discipline
jeanchastel
Use when a task involves heavy file reading, repo-wide search, or long tool output.
SkillAFreshness: AClaude Code +9 - 0.565score
bug-report
jeanchastel
Use when behavior looks like an Arkira harness defect in any repo, including bin/arkira, goal, gate, session state, hooks, or Arkira CI workflows.
SkillAFreshness: AClaude Code +9
Cite this page
design-system skill. Agent Mart. https://agentmart.dev/skills/jeanchastel-design-system (last updated 2026-10-24)