AGENT SKILL

building-ui-ux

Use when implementing user interfaces or user experiences - guides through exploration of design variations, frontend setup, iteration, and proper integration

适用职业设计师
使用场景前端开发
License 许可
MIT
最近更新
2026-11-14
Stars
★ 4.9k
Forks
590

01 前言 Front Matter

name
building-ui-ux
description
Use when implementing user interfaces or user experiences - guides through exploration of design variations, frontend setup, iteration, and proper integration

02 资源文件 6

03 SKILL.md 正文

<required> CRITICAL Add the following steps to your Todo list using TodoWrite:

  1. Ask user if they want to experiment with multiple UI variations or see a single design
  2. If user wants multiple variations, ask what kinds of variations to try
  3. If building a web frontend and it's not running, start the dev server and note the localhost URL
  4. Implement the UI/UX design(s)
  5. Ask user for feedback on the design
  6. Iterate based on feedback
  7. Ensure the new UI is properly wired up and integrated </required>

Building UI/UX

Overview

This skill guides you through implementing user interfaces and experiences with an emphasis on exploration, feedback, and proper integration.

Core principle: Explore variations, iterate with feedback, ensure proper integration.

Announce at start: "I'm using the Nori Building UI/UX skill to implement your interface."

The Process

Phase 1: Scope & Variation Planning

Ask the user:

"Would you like to:

  • See multiple UI variations to choose from?
  • Go with a single design approach?"

If multiple variations:

  • Ask what kinds of variations they want (e.g., minimalist vs rich, card-based vs list-based, light vs dark)
  • Aim for 2-4 distinct approaches
  • Plan to implement all variations in a way that allows easy comparison

Phase 2: Frontend Environment Setup

For web projects:

Check if the dev server is running:

  • If not, identify the start command (e.g., npm run dev, npm start)
  • Start the dev server
  • Note the localhost URL (typically http://localhost:3000 or similar)
  • Inform user: "Starting dev server at [URL]"

For other UI types:

  • Identify appropriate preview/testing mechanism
  • Set up accordingly

Phase 3: Implementation

When implementing multiple variations:

Stack variations in a way that makes comparison easy. For web UIs, this typically means:

  • Render all variations on a single page, stacked vertically
  • Add clear section dividers/headings for each variation
  • Use consistent spacing between variations
  • Ensure each variation is self-contained and functional

Example for React:

export default function UIExploration() {
  return (
    <div className="ui-exploration">
      <section className="variation">
        <h2>Variation 1: Minimalist</h2>
        <MinimalistLogin />
      </section>

      <section className="variation">
        <h2>Variation 2: Modern Gradient</h2>
        <ModernLogin />
      </section>

      <section className="variation">
        <h2>Variation 3: Classic Corporate</h2>
        <ClassicLogin />
      </section>
    </div>
  );
}

When implementing a single design:

  • Focus on clean, production-ready implementation
  • Follow project conventions and style guides
  • Ensure responsive design if applicable

Phase 4: Feedback & Iteration

Present to user:

  • Share the localhost URL or preview mechanism
  • Briefly describe each variation (if multiple)
  • Ask: "What do you think? Any changes you'd like to see?"

Iterate based on feedback:

  • Make requested changes
  • Continue asking for feedback until satisfied
  • Be ready to combine elements from different variations

Phase 5: Integration & Wiring

Ensure proper integration:

  • Remove exploration scaffolding (if used)
  • Wire up to actual data sources/APIs
  • Connect to routing/navigation
  • Add proper state management
  • Implement error handling
  • Add loading states if applicable
  • Test all interactive elements
  • Verify accessibility basics

Common integration points to check:

  • Form submissions → backend endpoints
  • Navigation → routing system
  • Authentication → auth context/store
  • Data fetching → API layer
  • Error boundaries → error handling
  • Responsive behavior → breakpoints

04 同仓库更多 Skills

microsoft
microsoft/FluidFramework

trigger-pipelines-for-copilot-pr

Trigger ADO pipelines for a Copilot-created PR by posting /azp run comments. Use when the user asks to trigger CI pipelines for a specific PR.

★ 4.9k
microsoft
microsoft/FluidFramework

review

Review changes relative to a prior state, such as a diff, pull request, branch, commit, or working-tree changes. Use for change-focused code review and regression analysis. Do not use to assess an existing file, API, design, implementation, or other artifact without a comparison; if the request is ambiguous, ask whether the user wants a change review and what prior state to compare against.

开发工程师代码审查后端与接口
★ 4.9k
microsoft
microsoft/FluidFramework

review-pr-local

The authority on pulling a pull request — Azure DevOps or GitHub — into an isolated local worktree so a human can review it in their editor, and on posting human-controlled review comments back to the PR (ADO via the ado PR-thread MCP tools or the Azure DevOps REST API, GitHub via the gh CLI). Auto-detects the platform and all identifiers from the PR URL; not tied to any specific repository. The AI assists an interactive human review and only ever posts comments the human explicitly requests. If you find yourself checking out a PR branch over the user's own working tree, or posting AI-authored review prose the human did not ask for, invoke this skill instead.

Skill与智能体开发
★ 4.9k
microsoft
microsoft/FluidFramework

policy-check

This skill should be used when the user asks to "run policy check", "check policy", "policy-check", or needs to validate package compliance. Provides guidance on running policy checks for specific packages or the entire repository.

★ 4.9k
microsoft
microsoft/FluidFramework

pipeline-test-triage

Triage test failures in an Azure DevOps pipeline run for Fluid Framework. Use when the user shares an ADO build/pipeline URL or build ID and wants failures analyzed, when they ask "why did this pipeline fail", "summarize the test failures", "is this test flaky or a real bug", "compare these runs", or wants bugs filed for genuine failures. Covers the Real Service End to End Tests pipeline as the worked example but applies to any FF test pipeline.

测试与质量
★ 4.9k
microsoft
microsoft/FluidFramework

fluid-release

Fluid Framework client release group — minor releases, patch releases, and post-release type test updates. Covers release prep, branching, version bumps, changelogs, release notes, and type test baselines. In autonomous mode, auto-detects state from the repo, attempts to execute, and falls back to a GitHub issue on failure. Triggers on "release", "do the release", "release status", version bump, release notes, changelog, release branch, or release engineering.

★ 4.9k