frontend-design-review

作者: microsoft

根據設計品質標準和你的設計系統審查 UI 實作,或從頭建立獨特且達到生產級水準的前端介面。

npx skills add https://github.com/microsoft/agent-skills --skill frontend-design-review

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:

  1. Review component in your Storybook / component library for API and usage
  2. Use Figma Dev Mode to get exact specs (spacing, tokens, properties)
  3. Implement using design system components + design tokens

During review:

  1. Compare implementation to Figma design
  2. Verify design tokens are used (not hardcoded values)
  3. Check all variants/states are implemented correctly
  4. Flag deviations (needs design approval)

If component doesn't exist:

  1. Check if existing component can be adapted
  2. Reach out to design for new component creation
  3. Document exception and rationale in code

Review Process

  1. Identify user task
  2. Check design system for matching patterns
  3. Evaluate aesthetic direction
  4. Identify scope (component, feature, or flow)
  5. Evaluate each pillar
  6. Score and prioritize issues (blocking/major/minor)
  7. 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.

來自 microsoft 的更多技能

oss-growth
microsoft
開源增長駭客角色
official
microsoft-foundry
microsoft
端到端部署、評估與管理 Foundry 代理:Docker 建置、ACR 推送、託管/提示代理建立、容器啟動、批次評估、持續評估、提示最佳化工作流程、agent.yaml、從追蹤資料集整理。用途:將代理部署至 Foundry、託管代理、建立代理、調用代理、評估代理、執行批次評估、持續評估、持續監控、持續評估狀態、最佳化提示、改善提示、提示最佳化器、最佳化代理指令、改善代理...
officialdevelopmentdevops
azure-ai
microsoft
用於 Azure AI:搜尋、語音、OpenAI、文件智慧。協助搜尋、向量/混合搜尋、語音轉文字、文字轉語音、轉錄、OCR。適用情境:AI 搜尋、查詢搜尋、向量搜尋、混合搜尋、語意搜尋、語音轉文字、文字轉語音、轉錄、OCR、將文字轉換為語音。
officialdevelopmentapi
azure-deploy
microsoft
對已準備好的應用程式執行 Azure 部署,這些應用程式需具備現有的 .azure/deployment-plan.md 與基礎架構檔案。當使用者要求建立新應用程式時,請勿使用此技能——應改用 azure-prepare。此技能會執行 azd up、azd deploy、terraform apply 及 az deployment 命令,並內建錯誤復原機制。需具備來自 azure-prepare 的 .azure/deployment-plan.md,以及來自 azure-validate 的驗證狀態。適用時機:「執行 azd up」、「執行 azd deploy」、「執行部署」……
officialdevopsaws
azure-storage
microsoft
Azure Storage Services 包括 Blob 儲存體、檔案共用、佇列儲存體、表格儲存體和 Data Lake。回答關於儲存存取層(熱、冷、凍結、封存)、各層使用時機及層級比較的問題。提供物件儲存、SMB 檔案共用、非同步訊息、NoSQL 鍵值及大數據分析。包含生命週期管理。用於:blob 儲存體、檔案共用、佇列儲存體、表格儲存體、data lake、上傳檔案、下載 blob、儲存帳戶、存取層...
officialdevelopmentdatabase
azure-diagnostics
microsoft
在 Azure 上使用 AppLens、Azure Monitor、資源健康狀態和安全分類來偵錯 Azure 生產問題。適用時機:偵錯生產問題、疑難排解應用程式服務、應用程式服務高 CPU、應用程式服務部署失敗、疑難排解容器應用程式、疑難排解函數、疑難排解 AKS、kubectl 無法連線、kube-system/CoreDNS 失敗、Pod 擱置、CrashLoop、節點未就緒、升級失敗、分析記錄、KQL、深入解析、映像提取失敗、冷啟動問題、健康狀態探查失敗...
officialdevopsdevelopment
azure-prepare
microsoft
準備 Azure 應用程式以進行部署(基礎架構 Bicep/Terraform、azure.yaml、Dockerfile)。用於建立/現代化或建立+部署;不適用於跨雲端遷移(請使用 azure-cloud-migrate)。請勿用於:copilot-sdk 應用程式(請使用 azure-hosted-copilot-sdk)。適用時機:「建立應用程式」、「建置 Web 應用程式」、「建立 API」、「建立無伺服器 HTTP API」、「建立前端」、「建立後端」、「建置服務」、「現代化應用程式」、「更新應用程式」、「新增驗證」、「新增快取」、「託管於 Azure」、「建立並...」
officialdevelopmentdevops
azure-validate
microsoft
部署前驗證 Azure 就緒狀態。對設定、基礎架構(Bicep 或 Terraform)、RBAC 角色指派、受控身分權限及先決條件進行深度檢查,再進行部署。適用時機:驗證我的應用程式、檢查部署就緒狀態、執行預檢檢查、驗證設定、確認是否可部署、驗證 azure.yaml、驗證 Bicep、部署前測試、疑難排解部署錯誤、驗證 Azure Functions、驗證函式應用程式、驗證無伺服器...
officialdevopstesting