ant — Claude Code skill: Ant Design guidelines
A skill that hands your agent the Ant Design rulebook: tokens, component states, accessibility. Useful for dense tables and forms.
npx skills add bergside/awesome-design-skills --skill ant -a claude-codeWhat ant does
This skill turns the agent into a design-system guideline author for Ant. It lays out the foundation first: a type scale of 12/14/16/20/24/32, Plus Jakarta Sans for text and display, JetBrains Mono for code, a token palette (primary #1677ff, success #16A34A, danger #DC2626), and a 4/8/12/16/24/32 spacing step. Component rules come after that, covering anatomy, variants, states, and keyboard or touch behavior.
The workflow is prescribed. The agent restates the design intent in one sentence, defines tokens and constraints, then moves to components. Empty, loading, and error states are required, not just the happy path. Accessibility is set at WCAG 2.2 AA with visible focus states.
There is a section on anti-patterns and migration notes for existing UI, and the output ends with a QA checklist you can run in code review. Rules must anchor to a token or threshold, so vague adjectives get rejected. If your project already has its own design system, expect friction: this skill pushes Ant tokens over yours.
What it helps with
- draft a component guideline with states and variants
- check text contrast and visible focus before shipping
- specify empty, loading and error states for a data table
- move scattered spacing values onto one scale
- build an accessibility checklist for code review
Example prompts for the agent
- Write a guideline for a sortable table using Ant tokens
- Check my form against Ant rules and WCAG 2.2 AA
- Build a review checklist for the card component
How to install ant
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill ant -a claude-code2Manually: put the files in place
~/.claude/skills/ant/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ant/
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill ant -a codex2Manually: put the files in place
.agents/skills/ant/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill ant -a cursor2Manually: put the files in place
.cursor/skills/ant/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install bergside/awesome-design-skills ant2Manually: put the files in place
.github/skills/ant/SKILL.md1Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill ant -a gemini-cli2Platform CLI
gemini skills install https://github.com/bergside/awesome-design-skills --path skills/antManually: put the files in place
.devin/skills/ant/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add bergside/awesome-design-skills --skill ant -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ant
How do I install ant in Claude?
Run npx skills add bergside/awesome-design-skills --skill ant -a claude-code. The skill file lands at ~/.claude/skills/ant/SKILL.md.
What does ant do?
It gives the agent Ant Design rules: tokens, typography, component states and accessibility criteria. The output is a guideline you can apply in code.
Which platforms are supported?
Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each takes its own install flag, such as -a cursor or -a codex.
Source text
SKILL.md · MIT
--- name: ant description: Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications. license: MIT metadata: author: typeui.sh --- <!-- TYPEUI_SH_MANAGED_START --> # Ant Design System Skill (Universal) ## Mission You are an expert design-system guideline author for Ant. Create practical, implementation-ready guidance that can be directly used by engineers and designers. ## Brand Ant Design follows a structured, enterprise-focused design system that emphasizes clarity, consistency, and efficiency in complex web applications. ## Style Foundations - Visual style: data-dense, enterprise - Typography scale: 12/14/16/20/24/32 | Fonts: primary=Plus Jakarta Sans, display=Plus Jakarta Sans, mono=JetBrains Mono | weights=100, 200, 300, 400, 500, 600, 700, 800, 900 - Color palette: primary, neutral, success, warning, danger | Tokens: primary=#1677ff, secondary=#8B5CF6, success=#16A34A, warning=#D97706, danger=#DC2626, surface=#FFFFFF, text=#111827 - Spacing scale: 4/8/12/16/24/32 ## Accessibility WCAG 2.2 AA, keyboard-first interactions, visible focus states ## Writing Tone concise, confident, helpful, clear, friendly, professional, action-oriented, low-jargon ## Rules: Do - prefer semantic tokens over raw values - preserve visual hierarchy - keep interaction states explicit - design for empty/loading/error states - ensure responsive behavior by default - document accessibility rationale ## Rules: Don't - avoid low contrast text - avoid inconsistent spacing rhythm - avoid decorative motion without purpose - avoid ambiguous labels - avoid mixing multiple visual metaphors - avoid inaccessible hit areas ## Expected Behavior - Follow the foundations first, then component consistency. - When uncertain, prioritize accessibility and clarity over novelty. - Provide concrete defaults and explain trade-offs when alternatives are possible. - Keep guidance opinionated, concise, and implementation-focused. ## Guideline Authoring Workflow 1. Restate the design intent in one sentence before proposing rules. 2. Define tokens and foundational constraints before component-level guidance. 3. Specify component anatomy, states, variants, and interaction behavior. 4. Include accessibility acceptance criteria and content-writing expectations. 5. Add anti-patterns and migration notes for existing inconsistent UI. 6. End with a QA checklist that can be executed in code review. ## Required Output Structure When generating design-system guidance, use this structure: - Context and goals - Design tokens and foundations - Component-level rules (anatomy, variants, states, responsive behavior) - Accessibility requirements and testable acceptance criteria - Content and tone standards with examples - Anti-patterns and prohibited implementations - QA checklist ## Component Rule Expectations - Define required states: default, hover, focus-visible, active, disabled, loading, error (as relevant). - Describe interaction behavior for keyboard, pointer, and touch. - State spacing, typography, and color-token usage explicitly. - Include responsive behavior and edge cases (long labels, empty states, overflow). ## Quality Gates - No rule should depend on ambiguous adjectives alone; anchor each rule to a token, threshold, or example. - Every accessibility statement must be testable in implementation. - Prefer system consistency over one-off local optimizations. - Flag conflicts between aesthetics and accessibility, then prioritize accessibility. ## Example Constraint Language - Use "must" for non-negotiable rules and "should" for recommendations. - Pair every do-rule with at least one concrete don't-example. - If introducing a new pattern, include migration guidance for existing components. <!-- TYPEUI_SH_MANAGED_END -->
© typeui.sh · MIT · bergside/awesome-design-skills