Token导航 LogoToken导航TokenDH.com
前端设计external-servicegithub未标认证来源可访问许可证需确认审计异常

design-intent-specialist设计意图专家

Agent Skill

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

总安装

416

周安装

17

GitHub Stars

12

下载量

133
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:design-intent-specialist(设计意图专家)
来源仓库:https://github.com/joaquimscosta/arkhe-claude-plugins
仓库路径:skills/design-intent-specialist
安装命令:
npx skills add https://github.com/joaquimscosta/arkhe-claude-plugins --skill design-intent-specialist
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/joaquimscosta/arkhe-claude-plugins --skill design-intent-specialist

简介

用于从视觉参考创建准确的前端实现,维护设计一致性。

  • 强调先理解现有设计模式,再分析冲突并制定实施计划。
  • 使用时必须首先检查 /design-intent/patterns/ 目录中的既有规范。
  • 安装方式:GitHub,命令为 npx skills add https://github.com/joaquimscosta/arkhe-claude-plugins --skill design-intent-specialist。
  • 注意:核心原则是视觉保真优先,遇到矛盾时采用智能冲突解决策略。

SKILL.md

Design Intent Specialist

Create accurate frontend implementations from visual references while maintaining design consistency.

Core Philosophy: Visual fidelity first, with intelligent conflict resolution when references clash with existing patterns.

Quick Start

1. Check Existing Patterns (Mandatory)

Before any implementation:

  1. Read /design-intent/patterns/ directory
  2. Report: "Existing patterns to consider: [list with values]"
  3. Understand established design decisions

2. Analyze Visual Reference

  • Extract visual elements for implementation
  • Identify potential conflicts with existing patterns
  • Plan implementation approach

3. Implement with Conflict Resolution

When visual references conflict with existing design intent:

  1. Implement the reference faithfully - This is what the user requested
  2. Flag conflicts clearly - "This design uses 8px spacing, but our intent specifies 12px"
  3. Ask for guidance - "Should I follow the design exactly, or adapt to established spacing?"
  4. Suggest implications - "If we use this spacing, should it become our new standard?"

4. Section-by-Section Implementation

For complex designs, break down into:

  • Header: Navigation, branding, user controls
  • Navigation: Menu items, hierarchies, states
  • Main Content: Primary content, data display, forms
  • Footer: Secondary links, metadata, actions

Each section analyzed for: layout, spacing, typography, responsiveness, visual treatment.

Implementation Priority

  1. Visual fidelity - Match the reference closely
  2. Existing components - Use established components where they fit
  3. Framework components - Leverage Fluent UI when appropriate
  4. Custom components - Create only when necessary for design accuracy

Custom Components

When creating custom components, use clear naming (CustomCard vs Card) and document with header comments. See WORKFLOW.md - Custom Component Documentation for the documentation template.

Behavioral Rules

  1. ALWAYS check existing design intent first - non-negotiable
  2. Visual fidelity over strict consistency - implement what's requested, flag conflicts
  3. Ask for guidance on conflicts - don't assume precedence
  4. Track custom components - for maintainability

MCP Integration

Optional: figma-dev-mode-mcp-server (Figma extraction) and fluent-pilot (Fluent UI guidance). Works without MCPs using screenshots.

Reference Documentation

Invocation

Triggered by:

  • Phase 5 of /design-intent workflow (automatic invocation)
  • User providing Figma URLs or screenshots
  • Requests to implement UI from visual references

Workflow Integration

When invoked from /design-intent Phase 5, architecture decisions and exploration are complete. Focus on execution with the richer context provided by the structured workflow.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.86%
按下载量换算46

Claude

30.37%
按下载量换算40

Cursor

19.75%
按下载量换算26

Gemini CLI

9.81%
按下载量换算13

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills