Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Magic Ui Component Generator

ASecurity

当需要生成或增强前端 UI 组件(定价表、表单、Hero、Logo/图标)时使用;借助 21st.dev Magic 生成多套差异化设计方案供选型并落地生产级 TypeScript 代码;不适用于纯逻辑/后端开发或需精确还原既有设计稿的场景;触发词:UI 组件、设计方案、Magic 21st.dev

3 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agentstypescriptgoreactnextjsfrontend

Works with

cursorclimcp

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add findscripter/everything-skills --skill magic-ui-component-generator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Magic Ui Component Generator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Magic Ui Component Generator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/findscripter-magic-ui-component-generator/badge)](https://www.skillsdirectory.com/skills/findscripter-magic-ui-component-generator)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: magic-ui-component-generator
title: AI UI 组件多方案生成
description: 当需要生成或增强前端 UI 组件(定价表、表单、Hero、Logo/图标)时使用;借助 21st.dev Magic 生成多套差异化设计方案供选型并落地生产级 TypeScript 代码;不适用于纯逻辑/后端开发或需精确还原既有设计稿的场景;触发词:UI 组件、设计方案、Magic 21st.dev
domain: 研发/frontend
triggers: [生成 UI 组件, 做一个定价表/表单/Hero, 给我几个设计方案, 美化现有组件, 需要 logo 或图标, Magic by 21st.dev]
tags: [frontend, ui-generation, design-variations, react, typescript, tailwind, 21st-dev]
level: 进阶
status: stable
agents: [claude-code, codex, cursor, gemini-cli]
tools: [Magic MCP (21st.dev), browser_subagent, SVGL]
requires: []
related: [shadcn-ui-components, web-component-design, frontend-design, web-artifacts-builder]
combines_with: [tailwind-css-patterns, react-state-management]
license: MIT
source: sickn33/agentic-awesome-skills
source_license: MIT
---
## 何时使用

当任务是**前端视觉层组件的创作或增强**,且追求超越通用模板的现代设计时,使用本技能。典型场景:

- 新建 UI 组件:定价表、联系表单、Hero 区块、卡片、导航等。
- 增强既有组件:加动画、改样式、补高级交互(粘性头、悬停动效等)。
- 为某功能头脑风暴多个设计方向、横向对比选型。
- 需要专业 logo 或图标(走内置 SVGL 集成)。

**不该用的边界:**

- 纯业务逻辑、状态管理、后端/接口开发——本技能只产出视觉组件。
- 需要像素级还原既有设计稿(Figma 切图)——本技能强调多方案发散,不是精确复刻。
- 缺少目标技术栈、可访问性/响应式要求等关键输入时,先停下来问清楚,不要硬生成。
- 生成结果不能替代环境内的真实测试、可访问性校验与专家评审。

## 步骤

1. **分析需求**:明确组件描述,确认产物匹配项目技术栈(如 Next.js / TypeScript / Tailwind CSS),并定义可访问性与响应式的明确约束。
2. **生成多方案**:通过 Magic MCP server 或 `browser_subagent` 访问 21st.dev/magic,针对同一组件生成**多套差异化、非常规风格**的方案,灵感取自 Shadcn UI、Magic UI、Aceternity 等真实组件库。
3. **并列呈现选项**:简要描述各方案,并列对比风格差异、布局思路与高级特性(粘性头、悬停动画等),交由使用者挑选。
4. **集成所选方案**:选定后,落地完整可用的生产级 TypeScript 代码;确认依赖已安装(如 `lucide-react`、`framer-motion`);正确处理 props、类型与响应式行为。

## 指令

- **强制:必须出方案后再落地**。在把最终代码写入项目前,**始终先提供多套高质量设计变体**供选择(Choice First)。
- **拒绝平庸**:不要生成通用、保守、千篇一律的样式,主动突破边界做出有创意、视觉惊艳的 UI/UX。
- **整洁代码**:所有产物为干净的 TypeScript,满足可访问(accessible)与响应式(responsive)。
- **完全接管**:将生成的组件视为项目自有代码,负责其类型、props 与后续维护。

## 示例

提示词要主动推向现代美学,越具体越好:

- `avant-garde SaaS pricing table with glassmorphism and animated borders`(前卫 SaaS 定价表,玻璃拟态 + 动画边框)
- `highly immersive contact form with dynamic floating labels`(沉浸式联系表单,动态浮动标签)

典型对话流:使用者说"做一个 Hero 区块" → 生成 3 套风格(极简渐变 / 玻璃拟态 / 暗色霓虹)→ 并列描述差异 → 使用者选"玻璃拟态" → 落地 TS 代码并补 `framer-motion` 依赖。

## 注意事项

- 仅在任务明确落在上述范围内时使用,避免越界处理逻辑/后端类需求。
- 多方案是核心价值:即便使用者只要一个,也应先给出对比选项再收敛。
- 集成阶段务必核对依赖安装与类型正确,避免交付即报错。
- 产物需经环境内验证与评审后方可视为完成。

## 互见

- 前端组件库 / 设计系统相关技能(Shadcn UI、Tailwind 规范)
- Figma 设计稿读取与还原类技能(精确复刻场景的替代选择)

---

采编自 [sickn33/antigravity-awesome-skills](https://21st.dev/magic)(MIT 许可)。

Attribution

findscripterfindscripter
View sourceSee grades on GitHubMore from findscripter →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →