Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Skill Open Design Ui

ASecurity

Use for defining and implementing a distinctive frontend visual system with design direction, tokens, component patterns, responsive UI, anti-generic decisions, and visual QA after the experience strategy is clear.

53 stars
0 votes
0 copies
0 views
Added 9/26/2026
ai-agentsgorailsgitfrontend

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add IAPro-Community/Orquestrador-Maestro --skill skill-open-design-ui --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Open Design Ui?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Open Design Ui
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/iapro-community-skill-open-design-ui/badge)](https://www.skillsdirectory.com/skills/iapro-community-skill-open-design-ui)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: skill-open-design-ui
description: Use for defining and implementing a distinctive frontend visual system with design direction, tokens, component patterns, responsive UI, anti-generic decisions, and visual QA after the experience strategy is clear.
category: frontend
risk: low
source: https://github.com/nexu-io/open-design
---

# Skill Open Design UI

Use this skill for the visual-system and interface-design layer of a frontend task. It works with the project’s existing framework and styling system. For a full premium marketing experience, use `skill-premium-web-experience` first; this skill turns the approved direction into a coherent visual and component system.

## Scope

Own:

- design direction and visual language;
- typography, color, shape, depth, composition, spacing, grid, hierarchy, lighting, and texture;
- design tokens, component rules, responsive UI, and visual QA;
- anti-generic refinement without breaking product behavior.

Do not own the complete business discovery, narrative architecture, conversion strategy, or scroll-story decision. Refer those to `skill-premium-web-experience`. Use a specialized scroll implementation skill only when it is available and the narrative requires it.

## Workflow

1. Inspect the real surface, existing brand cues, `PRODUCT.md`, `DESIGN.md`, tokens, components, routes, icons, imagery, breakpoints, and states before editing.
2. Name one visual direction such as Modern Minimal, Tech Utility, Editorial, Bold Product, or Calm Enterprise. Explain why it fits the audience and surface.
3. Convert the direction into tokens for type scale, font roles, surfaces, borders, accents, elevation, spacing, radius, density, container width, and motion.
4. Apply the system to the smallest complete slice that includes the real content and states touched by the task.
5. Preserve routes, form semantics, analytics, permissions, localization, and existing interaction contracts.
6. Validate at mobile, tablet, and desktop sizes, then run the available lint, typecheck, build, targeted tests, and browser/screenshot checks.

## Visual Rules

- Use existing tokens first; introduce local variables only when a real gap exists.
- Keep repeated components consistent in radius, border, shadow, spacing, density, and icon treatment.
- Use cards for grouped data, repeated items, or framed tools; do not put every section in a floating panel or nest cards by default.
- Prefer real product screenshots, product states, or faithful UI previews over generic illustrations.
- Use a distinctive hierarchy and composition; do not add decoration that lacks a product or narrative reason.
- Avoid default purple/cyan palettes, decorative gradient text, gratuitous glassmorphism/glows, side-tab borders, extreme radii, flat typography, giant icon tiles, and motion without meaning.
- Keep copy specific, correctly spelled, localized, and UTF-8 safe.

## Responsive UI

Treat mobile as a designed composition. Define how navigation, type scale, spacing, media, grids, sticky regions, and touch interactions change at `320x568`, `390x844`, `768x1024`, `1024x768`, and a representative desktop width. Verify long labels, localized content, overflow, focus states, disabled states, and realistic data.

## Visual QA

Inspect the rendered page, not only the source or build output. Check hierarchy, line breaks, clipping, overlap, contrast, blank media, layout shift, animation glitches, and the first viewport’s clarity. Confirm that the primary action and status are understandable quickly. Compare before/after when refining an existing surface and report residual visual risk.

## Impeccable Vocabulary

When useful, classify the smallest intervention as `shape`, `craft`, `critique`, `polish`, `typeset`, `layout`, `colorize`, `animate`, `clarify`, `adapt`, `distill`, `quieter`, or `bolder`. Treat generated suggestions as options to evaluate, not authority. If the request is “genérico”, “parece feito por IA”, “mais profissional”, or “mais premium”, use this vocabulary to choose a bounded visual intervention instead of redesigning unrelated surfaces.

## Optional CLI

If the project already provides the Impeccable CLI, `npx impeccable detect <target>` is an additional deterministic signal. Do not install dependencies or enable live hooks automatically, and do not treat the command as a replacement for visual, accessibility, or browser QA.

## Done Criteria

- The visual direction is explicit and visible in the implemented surface.
- Tokens and repeated components are coherent.
- The first viewport communicates the real product, offer, or working surface.
- Responsive behavior and interaction states remain usable.
- Accessibility, content quality, existing contracts, and visual integrity were checked.

## Related Skills

- `skill-premium-web-experience` — complete experience strategy and narrative orchestration.
- `skill-modern-ui-patterns` — component composition and product interaction states.
- `skill-frontend-ux-guardrails` — final usability, accessibility, responsive, and layout gate.
- `skill-product-ux-architecture` — app-wide information architecture, navigation, screen inventory, and journeys.
- `skill-design-engineering-craft` — high-fidelity implementation details after the visual direction is clear.
- `skill-motion-design-principles` — timing, easing, choreography, interruption, and reduced-motion behavior.
- `skill-impeccable` — focused critique and polish requests.

Attribution

IAPro-CommunityIAPro-Community
View sourceSee grades on GitHubMore from IAPro-Community →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →