Agent skill
frontend-design-review
Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craft, and trustworthy building. USE FOR: PR reviews, design reviews, accessibility audits, design system compliance checks, creative frontend design, UI code review, component reviews, responsive design checks, theme testing, and creating memorable UI. DO NOT USE FOR: Backend API reviews, database schema reviews, infrastructure or DevOps work, pure business logic without UI, or non-frontend code.
Install this agent skill to your Project
npx add-skill https://github.com/microsoft/skills/tree/main/.github/skills/frontend-design-review
SKILL.md
Frontend Design Review
Review UI implementations against design quality standards and your design system OR create distinctive, production-grade frontend interfaces from scratch.
Two Modes
Mode 1: Design Review
Evaluate existing UI for design system compliance, three quality pillars (Frictionless, Quality Craft, Trustworthy), accessibility, and code quality.
Mode 2: Creative Frontend Design
Create distinctive interfaces that avoid generic "AI slop" aesthetics, have clear conceptual direction, and execute with precision.
Creative Frontend Design
Before coding, commit to an aesthetic direction:
- Purpose: What problem does this solve? Who uses it?
- Tone: minimal, maximalist, retro-futuristic, organic, luxury, playful, editorial, brutalist, art deco, soft/pastel, industrial, etc.
- Constraints: Framework, performance, accessibility requirements.
- Differentiation: What makes this distinctive and context-appropriate?
Aesthetics Guidelines
- Typography: Distinctive fonts that elevate aesthetics. Pair a display font with a refined body font. Avoid Inter, Roboto, Arial, Space Grotesk.
- Color & Theme: Cohesive palette with CSS variables. Dominant colors + sharp accents > timid, evenly-distributed palettes.
- Motion: CSS-only preferred. One well-orchestrated page load with staggered reveals > scattered micro-interactions.
- Spatial Composition: Asymmetry, overlap, diagonal flow, grid-breaking elements, generous negative space OR controlled density.
- Backgrounds: Gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, grain overlays.
AVOID: Overused fonts, cliched color schemes, predictable layouts, cookie-cutter design without context-specific character.
Match implementation complexity to vision. Maximalist = elaborate code. Minimalist = restraint and precision.
Design Review
Design System Workflow
Before implementing:
- Review component in your Storybook / component library for API and usage
- Use Figma Dev Mode to get exact specs (spacing, tokens, properties)
- Implement using design system components + design tokens
During review:
- Compare implementation to Figma design
- Verify design tokens are used (not hardcoded values)
- Check all variants/states are implemented correctly
- Flag deviations (needs design approval)
If component doesn't exist:
- Check if existing component can be adapted
- Reach out to design for new component creation
- Document exception and rationale in code
Review Process
- Identify user task
- Check design system for matching patterns
- Evaluate aesthetic direction
- Identify scope (component, feature, or flow)
- Evaluate each pillar
- Score and prioritize issues (blocking/major/minor)
- Provide recommendations with design system examples
Core Principles
- Task completion: Minimum clicks. Every screen answers "What can I do?" and "What happens next?"
- Action hierarchy: 1-2 primary actions per view. Progressive disclosure for secondary.
- Onboarding: Explain features on introduction. Smart defaults over configuration.
- Navigation: Clear entry/exit points. Back/cancel always available. Breadcrumbs for deep flows.
Quality Pillars
1. Frictionless Insight to Action
Evaluate: Task completable in ≤3 interactions? Primary action obvious and singular?
Red flags: Excessive clicks, multiple competing primary buttons, buried actions, dead ends.
2. Quality is Craft
Evaluate:
- Design system compliance: matches Figma specs, uses design tokens
- Aesthetic direction: distinctive typography, cohesive colors, intentional motion
- Accessibility: Grade C minimum (WCAG 2.1 A), Grade B ideal (WCAG 2.1 AA)
Red flags: Generic AI aesthetics, hardcoded values, implementation doesn't match Figma, broken reflow, missing focus indicators.
3. Trustworthy Building
Evaluate:
- AI transparency: disclaimer on AI-generated content
- Error transparency: actionable error messages
Red flags: Missing AI disclaimers, opaque errors without guidance.
Review Output Format
See references/review-output-format.md for the full review template.
Review Type Modifiers
See references/review-type-modifiers.md for context-specific review focus areas (PR, Creative, Design, Accessibility).
Quick Checklist
See references/quick-checklist.md for the pre-approval checklist covering design system compliance, aesthetic quality, frictionless, quality craft, and trustworthy pillars.
Pattern Examples
See references/pattern-examples.md for good/bad examples of creative frontend and design system review work.
Acknowledgments
Creative frontend principles inspired by Anthropic's frontend-design skill. Design review principles and quality pillar framework created by @Quirinevwm for systematic UI evaluation.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
podcast-generation
Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).
entra-agent-id
Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation. Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker/Kubernetes), 3P agent integration, autonomous and interactive agent patterns. Triggers: "agent identity", "agent id", "Agent Identity Blueprint", "BlueprintPrincipal", "entra agent", "agent identity provisioning", "Graph agent identity", "entra sidecar", "agent id sidecar", "auth sidecar", "3P agent", "third-party agent identity", "polyglot agent auth".
github-issue-creator
Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.
copilot-sdk
Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, custom agents, skills, and deployment patterns. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).
continual-learning
Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.
Didn't find tool you were looking for?