ui-ux
Fallback for user-facing interface work when frontend-design is unavailable; keep UI clear, accessible, responsive, and intentional without unnecessary…
Skill by prinx
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/prinx-ui-ux
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
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/ui-ux
What's inside
- Skill name
ui-ux- Description
- Fallback for user-facing interface work when frontend-design is unavailable; keep UI clear, accessible, responsive, and intentional without unnecessary design-system work.
- License
- MIT
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# UI/UX Fallback Use this skill only when a skill named `frontend-design` is not available. Read `core/standards/ui-design.md` for the project's design preferences before starting any UI work. Preserve the existing application's visual and interaction conventions. A simple UI can still be polished and intentional: build the smallest interface that satisfies the approved feature with clear hierarchy, understandable labels and feedback, semantic HTML, keyboard access, visible focus, sufficient contrast, and responsive behavior at relevant sizes. Reuse existing components and styles before creating new ones. **Follow emotional design at three levels (visceral, behavioral, reflective):** - **Visceral**: clean, airy, intentional at first glance. No jarring colors, no clutter. - **Behavioral**: smooth interactions, responsive feedback, effortless navigation. Buttons feel satisfying, forms are frictionless, loading states are intentional. - **Reflective**: moments of delight that build brand loyalty. Thoughtful microcopy, satisfying completion states, a design the user would recommend. **Key design directions (see `core/standards/ui-design.md` for full detail):** - No AI-generated-looking UI. No dark purple, no ugly borders. - Fonts should be inspired by the target domain of the app (music → score-like fonts, architecture → blueprint lettering, etc.) - No boring centered hero landing pages. Be creative with layout — asymmetric, split, staggered, narrative-driven. - White or white-variant dominated for light mode. Dark mode follows the brand. - Google-level simplicity: straightforward, well-organized, hides complexity. - Mobile-first. Dribbble quality bar, but unique per project. Do not invent a design system, add decorative complexity, or expand scope with unrelated screens, states, or abstractions. Cover only the loading, empty, error, and success states the feature actually needs. If conventions are missing, choose a simple reversible presentation and note it briefly.
From prinx/agents, MIT.
More from prinx/agents
- 0.518score
orchestrate
prinx
Use when classifying engineering work, selecting a fast or full workflow path, and coordinating agent handoffs.
SkillBFreshness: BClaude Code +9 - 0.518score
quality-review
prinx
Use when reviewing a ticket diff for correctness, regressions, architecture, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.513score
branch-safely
prinx
Use before implementation when checking repository state, selecting a branch, or protecting uncommitted work.
SkillBFreshness: BClaude Code +9 - 0.473score
deploy-vercel
prinx
Use when an approved, human-requested deployment specifically targets Vercel.
SkillCFreshness: CClaude Code +9 - 0.473score
e2e-testing
prinx
Use when a user journey or cross-service behavior needs end-to-end validation.
SkillCFreshness: CClaude Code +9 - 0.473score
feature-testing
prinx
Use when validating a completed feature against its acceptance criteria through integrated behavior.
SkillCFreshness: CClaude Code +9 - 0.473score
unit-testing
prinx
Use when creating or running focused automated tests for isolated logic and edge cases.
SkillCFreshness: CClaude Code +9 - 0.470score
deploy-vps
prinx
Use when deploying to a VPS via GitHub Actions and Docker.
SkillCFreshness: CClaude Code +9 - 0.469score
requirements-gathering
prinx
Use when a request needs product discovery, scope, acceptance criteria, constraints, or high-value clarification questions.
SkillCFreshness: CClaude Code +9 - 0.469score
deploy
prinx
Use only for a human-requested deployment after QA PASS and review APPROVE have been recorded.
SkillCFreshness: CClaude Code +9 - 0.469score
task-breakdown
prinx
Use when converting a plan into ordered, independently verifiable engineering backlog tickets.
SkillCFreshness: CClaude Code +9 - 0.469score
solution-design
prinx
Use when translating approved requirements into a solution design, architecture fit, risks, and test strategy.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 29, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/prinx/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from prinx
- 0.518score
quality-review
prinx
Use when reviewing a ticket diff for correctness, regressions, architecture, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.518score
orchestrate
prinx
Use when classifying engineering work, selecting a fast or full workflow path, and coordinating agent handoffs.
SkillBFreshness: BClaude Code +9 - 0.513score
branch-safely
prinx
Use before implementation when checking repository state, selecting a branch, or protecting uncommitted work.
SkillBFreshness: BClaude Code +9 - 0.473score
unit-testing
prinx
Use when creating or running focused automated tests for isolated logic and edge cases.
SkillCFreshness: CClaude Code +9 - 0.473score
deploy-vercel
prinx
Use when an approved, human-requested deployment specifically targets Vercel.
SkillCFreshness: CClaude Code +9 - 0.473score
e2e-testing
prinx
Use when a user journey or cross-service behavior needs end-to-end validation.
SkillCFreshness: CClaude Code +9
Cite this page
ui-ux skill. Agent Mart. https://agentmart.dev/skills/prinx-ui-ux (last updated 2026-10-24)