frontend-design（前端设计）

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task: - Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. - Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. - Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. - Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. - When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. - Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. - Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. - Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. - Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. - Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Quick Summary

Goal: Create distinctive, production-grade frontend interfaces with high design quality, avoiding generic AI aesthetics.

Workflow:

1. Detect Input Type — Screenshot/image provided vs building from scratch
2. Extract Design Guidelines — For screenshots: analyze colors, typography, spacing, layout via ai-multimodal
3. Design Thinking — Choose bold aesthetic direction (tone, differentiation, constraints)
4. Implement Code — Production-grade, visually striking, cohesive code
5. Verify Quality — Compare implementation to original design/vision

Key Rules:

Frontend/UI Context (if applicable)

When this task involves frontend or UI changes,

UI System Context — For ANY task touching .ts, .html, .scss, or .css files: MUST ATTENTION READ before implementing: 1. docs/project-reference/frontend-patterns-reference.md — component base classes, stores, forms 2. docs/project-reference/scss-styling-guide.md — BEM methodology, SCSS variables, mixins, responsive 3. docs/project-reference/design-system/README.md — design tokens, component inventory, icons Reference docs/project-config.json for project-specific paths.

• Component patterns: docs/project-reference/frontend-patterns-reference.md (content auto-injected by hook — check for [Injected:...] header before reading)
• Styling/BEM guide: docs/project-reference/scss-styling-guide.md
• Design system tokens: docs/project-reference/design-system/README.md
• For screenshot inputs, extract design guidelines FIRST before coding
• Never use generic fonts (Inter, Roboto, Arial) or cliched color schemes
• Match implementation complexity to aesthetic vision (maximalist = elaborate, minimalist = precise)

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.

The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.

Prerequisites

⚠️ MUST ATTENTION READ references/design-extraction-overview.md before executing screenshot-based workflows — contains design guideline extraction protocols, analysis prompts, and visual verification methods required by the screenshot/image input workflow below. For asset generation workflows, also ⚠️ MUST ATTENTION READ references/asset-generation.md.

Input Types & Workflows

When User Provides Screenshot/Image/Design Reference

MANDATORY workflow for screenshot/image/design inputs:

1. Extract Design Guidelines using ./references/design-extraction-overview.md:

- Analyze screenshot/image with ai-multimodal skill - Extract: colors (hex codes), typography (fonts, sizes, weights), spacing scale, layout patterns, visual hierarchy - Document findings in project docs/design-guidelines/extracted-design.md - See ./references/extraction-prompts.md for comprehensive analysis prompts

1. Implement Code following extracted guidelines:

- Use exact colors from extraction (hex codes) - Match typography specifications (fonts, sizes, weights, line-heights) - Replicate layout structure and spacing system - Maintain visual hierarchy and component patterns - Preserve aesthetic direction and mood

1. Verify Quality using ./references/visual-analysis-overview.md:

- Compare implementation to original screenshot - Check color accuracy, spacing consistency, typography matching - Ensure all design elements preserved

Important: Do NOT skip to implementation. Extract design guidelines FIRST, then code.

When Building from Scratch (No Screenshot Provided)

Follow "Design Thinking" process below to create original design.

Design Thinking

Before coding, understand the context and commit to a BOLD aesthetic direction:

• Purpose: What problem does this interface solve? Who uses it?
• Tone: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
• Constraints: Technical requirements (framework, performance, accessibility).
• Differentiation: What makes this UNFORGETTABLE? What's the one thing someone will remember?

CRITICAL: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.

Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is:

• Production-grade and functional
• Visually striking and memorable
• Cohesive with a clear aesthetic point-of-view
• Meticulously refined in every detail

Frontend Aesthetics Guidelines

Focus on:

• Typography: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font.
• Color & Theme: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.
• Motion: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available (Use anime.js for animations: ./references/animejs.md). Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.
• Spatial Composition: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density.
• Backgrounds & Visual Details: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays.
• Visual Assets: Use ai-multimodal skills to generate the assets and media-processing skill to remove the background of generated assets if needed

Working with Visual Assets

Quick Start: ./references/ai-multimodal-overview.md

Generating New Visual Assets

When you need to GENERATE new hero images, backgrounds, textures, or decorative elements that match the design aesthetic, use the ai-multimodal skill. This ensures generated assets align with the design thinking and aesthetics guidelines rather than producing generic imagery.

Analyzing Provided Screenshots/Images/Designs

When user provides screenshots, photos, or design references to analyze or replicate, use ./references/design-extraction-overview.md to extract design guidelines BEFORE implementation. This is MANDATORY for screenshot inputs (see "Input Types & Workflows" above).

Workflows:

• ./references/asset-generation.md - Generate design-aligned visual assets
• ./references/visual-analysis-overview.md - Analyze and verify asset quality (modular)
• ./references/design-extraction-overview.md - Extract guidelines from inspiration (modular)
• ./references/technical-overview.md - Optimization and best practices (modular)

Each overview references detailed sub-modules for progressive disclosure.

NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.

Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.

IMPORTANT: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.

Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.

Related

• interface-design — Product UIs (dashboards, admin panels, SaaS apps)
• ui-ux-pro-max
• shadcn-tailwind

Closing Reminders

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:
• MANDATORY IMPORTANT MUST ATTENTION read frontend-patterns-reference, scss-styling-guide, design-system/README before any UI change.
• MANDATORY IMPORTANT MUST ATTENTION READ references/design-extraction-overview.md before starting
• MANDATORY IMPORTANT MUST ATTENTION READ references/asset-generation.md before starting
• MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
• MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.