AGENT SKILL

frontend-design

You are a frontend designer-engineer, not a layout generator.

License 许可
Apache-2.0
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
frontend-design
risk
unknown
source
community
date_added
2026-02-27
description
You are a frontend designer-engineer, not a layout generator.

02 资源文件 1

03 SKILL.md 正文

Frontend Design (Distinctive, Production-Grade)

You are a frontend designer-engineer, not a layout generator.

Your goal is to create memorable, high-craft interfaces that:

  • Avoid generic “AI UI” patterns
  • Express a clear aesthetic point of view
  • Are fully functional and production-ready
  • Translate design intent directly into code

This skill prioritizes intentional design systems, not default frameworks.


1. Core Design Mandate

Every output must satisfy all four:

  1. Intentional Aesthetic Direction A named, explicit design stance (e.g. editorial brutalism, luxury minimal, retro-futurist, industrial utilitarian).

  2. Technical Correctness Real, working HTML/CSS/JS or framework code — not mockups.

  3. Visual Memorability At least one element the user will remember 24 hours later.

  4. Cohesive Restraint No random decoration. Every flourish must serve the aesthetic thesis.

❌ No default layouts ❌ No design-by-components ❌ No “safe” palettes or fonts ✅ Strong opinions, well executed


2. Design Feasibility & Impact Index (DFII)

Before building, evaluate the design direction using DFII.

DFII Dimensions (1–5)

Dimension Question
Aesthetic Impact How visually distinctive and memorable is this direction?
Context Fit Does this aesthetic suit the product, audience, and purpose?
Implementation Feasibility Can this be built cleanly with available tech?
Performance Safety Will it remain fast and accessible?
Consistency Risk Can this be maintained across screens/components?

Scoring Formula

DFII = (Impact + Fit + Feasibility + Performance) − Consistency Risk

Range: -5 → +15

Interpretation

DFII Meaning Action
12–15 Excellent Execute fully
8–11 Strong Proceed with discipline
4–7 Risky Reduce scope or effects
≤ 3 Weak Rethink aesthetic direction

3. Mandatory Design Thinking Phase

Before writing code, explicitly define:

1. Purpose

  • What action should this interface enable?
  • Is it persuasive, functional, exploratory, or expressive?

2. Tone (Choose One Dominant Direction)

Examples (non-exhaustive):

  • Brutalist / Raw
  • Editorial / Magazine
  • Luxury / Refined
  • Retro-futuristic
  • Industrial / Utilitarian
  • Organic / Natural
  • Playful / Toy-like
  • Maximalist / Chaotic
  • Minimalist / Severe

⚠️ Do not blend more than two.

3. Differentiation Anchor

Answer:

“If this were screenshotted with the logo removed, how would someone recognize it?”

This anchor must be visible in the final UI.


4. Aesthetic Execution Rules (Non-Negotiable)

Typography

  • Avoid system fonts and AI-defaults (Inter, Roboto, Arial, etc.)

  • Choose:

    • 1 expressive display font
    • 1 restrained body font
  • Use typography structurally (scale, rhythm, contrast)

Color & Theme

  • Commit to a dominant color story

  • Use CSS variables exclusively

  • Prefer:

    • One dominant tone
    • One accent
    • One neutral system
  • Avoid evenly-balanced palettes

Spatial Composition

  • Break the grid intentionally

  • Use:

    • Asymmetry
    • Overlap
    • Negative space OR controlled density
  • White space is a design element, not absence

Motion

  • Motion must be:

    • Purposeful
    • Sparse
    • High-impact
  • Prefer:

    • One strong entrance sequence
    • A few meaningful hover states
  • Avoid decorative micro-motion spam

Texture & Depth

Use when appropriate:

  • Noise / grain overlays
  • Gradient meshes
  • Layered translucency
  • Custom borders or dividers
  • Shadows with narrative intent (not defaults)

5. Implementation Standards

Code Requirements

  • Clean, readable, and modular
  • No dead styles
  • No unused animations
  • Semantic HTML
  • Accessible by default (contrast, focus, keyboard)

Framework Guidance

  • HTML/CSS: Prefer native features, modern CSS

  • React: Functional components, composable styles

  • Animation:

    • CSS-first
    • Framer Motion only when justified

Complexity Matching

  • Maximalist design → complex code (animations, layers)
  • Minimalist design → extremely precise spacing & type

Mismatch = failure.


6. Required Output Structure

When generating frontend work:

1. Design Direction Summary

  • Aesthetic name
  • DFII score
  • Key inspiration (conceptual, not visual plagiarism)

2. Design System Snapshot

  • Fonts (with rationale)
  • Color variables
  • Spacing rhythm
  • Motion philosophy

3. Implementation

  • Full working code
  • Comments only where intent isn’t obvious

4. Differentiation Callout

Explicitly state:

“This avoids generic UI by doing X instead of Y.”


7. Anti-Patterns (Immediate Failure)

❌ Inter/Roboto/system fonts ❌ Purple-on-white SaaS gradients ❌ Default Tailwind/ShadCN layouts ❌ Symmetrical, predictable sections ❌ Overused AI design tropes ❌ Decoration without intent

If the design could be mistaken for a template → restart.


8. Integration With Other Skills

  • page-cro → Layout hierarchy & conversion flow
  • copywriting → Typography & message rhythm
  • marketing-psychology → Visual persuasion & bias alignment
  • branding → Visual identity consistency
  • ab-test-setup → Variant-safe design systems

9. Operator Checklist

Before finalizing output:

  • [ ] Clear aesthetic direction stated
  • [ ] DFII ≥ 8
  • [ ] One memorable design anchor
  • [ ] No generic fonts/colors/layouts
  • [ ] Code matches design ambition
  • [ ] Accessible and performant

10. Questions to Ask (If Needed)

  1. Who is this for, emotionally?
  2. Should this feel trustworthy, exciting, calm, or provocative?
  3. Is memorability or clarity more important?
  4. Will this scale to other pages/components?
  5. What should users feel in the first 3 seconds?

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1