Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计提醒

explainer-visuals解释者视觉效果

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

475

周安装

20

GitHub Stars

35

下载量

166
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:explainer-visuals(解释者视觉效果)
来源仓库:https://github.com/petekp/claude-code-setup
仓库路径:skills/explainer-visuals
安装命令:
npx skills add https://github.com/petekp/claude-code-setup --skill explainer-visuals
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/petekp/claude-code-setup --skill explainer-visuals

简介

用于辅助界面设计、视觉规范和交互体验优化。

  • 适合整理页面结构、生成 UI 方案或改进组件层级。
  • 需要结合品牌、设计系统和用户任务使用。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • 涉及真实页面改动时应通过截图检查文本溢出和对齐。
  • explainer-visuals 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Explainer Visuals

Create animated, interactive visuals that make complex ideas intuitive.

Philosophy

Great explainer visuals don't just illustrate—they *reveal*. They show the structure hidden in complexity, the motion implicit in static descriptions, the relationships that words struggle to convey.

Core principles:

  • Earned complexity: Start simple, add layers through interaction or animation
  • Semantic motion: Movement carries meaning, not just attention
  • Readable at rest: The static state communicates the core idea
  • Progressive disclosure: Let viewers control depth of exploration

Discovery Process

Before creating any visual, conduct a brief discovery interview using AskUserQuestion. Understand not just WHAT to visualize, but WHY this idea needs visual treatment.

Discovery Questions

Ask 1-2 focused questions from these categories:

Understanding the idea:

  • "What's the single most important insight viewers should take away?"
  • "What makes this concept hard to explain in words alone?"
  • "Is there a common misconception this visual should correct?"

Understanding the context:

  • "Where will this appear in your essay? (Opening hook, supporting evidence, climactic reveal, summary)"
  • "What's the surrounding content's tone? (Academic, conversational, provocative, instructive)"

Understanding the audience:

  • "What does your reader already know about this topic?"
  • "Should this feel like a quick insight or an explorable deep-dive?"

Skip discovery only if the user has already provided rich context about their goals.

Visual Format Selection

Choose format based on the nature of the idea:

Concept TypeOptimal FormatWhy
Transformation/ChangeMorphing animationShows before→after as continuous process
Hierarchy/StructureZoomable treemap or nested diagramReveals layers through interaction
Process/FlowStepped animation with scrubberUser controls pace of revelation
ComparisonSide-by-side with synchronized animationParallel structure highlights differences
Accumulation/GrowthBuilding animationEach element adds to previous
Relationship/NetworkForce-directed graphReveals emergent structure
Distribution/ProportionAnimated unit chart or waffleMakes quantities tangible
Cycle/FeedbackLooping animation with entry pointsShows perpetual motion of systems
Timeline/SequenceHorizontal scroll with annotationsNatural reading direction
Spatial/GeographicAnnotated map with zoomGrounds abstract in physical
Mental ModelMetaphor-based diagramConnects abstract to familiar
Trade-off/TensionSlider-controlled balanceShows interdependence

Design System

Typography

font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;

--text-hero: 2rem;      /* Single key number or word */
--text-title: 1.25rem;  /* Visual title */
--text-label: 0.875rem; /* Axis labels, annotations */
--text-micro: 0.75rem;  /* Secondary details */

Color Palettes

Minimal (default):

--ink: #1a1a2e;        /* Primary elements */
--ink-light: #4a4a68;  /* Secondary elements */
--accent: #e94560;     /* Single highlight */
--ground: #fafafa;     /* Background */
--ground-alt: #f0f0f5; /* Alternate regions */

Data-rich (when showing categories):

--cat-1: #4e79a7; --cat-2: #f28e2c; --cat-3: #e15759;
--cat-4: #76b7b2; --cat-5: #59a14f; --cat-6: #af7aa1;

Adapt to essay context:

  • Technical/analytical → cooler palette, more contrast
  • Personal/reflective → warmer palette, softer edges
  • Provocative/challenging → bolder accent, higher saturation

Motion Principles

const EASE = {
  standard: 'cubic-bezier(0.4, 0, 0.2, 1)',  // Smooth, natural
  enter: 'cubic-bezier(0, 0, 0.2, 1)',       // Start fast, settle
  exit: 'cubic-bezier(0.4, 0, 1, 1)',        // Start slow, accelerate
  bounce: 'cubic-bezier(0.34, 1.56, 0.64, 1)' // Slight overshoot
};

const DURATION = {
  micro: 100,    // Color, opacity
  fast: 200,     // Small movements
  medium: 350,   // Standard transitions
  slow: 500,     // Large movements
  dramatic: 800  // Major reveals
};

Motion semantics:

  • Fade = existence (appear/disappear)
  • Scale = importance (emphasize/de-emphasize)
  • Translate = relationship (group/separate)
  • Morph = identity (transform)
  • Rotate = state (toggle, cycle)

Technology Selection

Choose the simplest tool that achieves the effect:

ComplexityToolUse When
SimplePure CSSState transitions, hovers, basic transforms
StandardVanilla JS + CSSSequenced animations, scroll triggers, simple interactions
ComplexGSAPTimeline sequences, physics, SVG morphing
Data-drivenD3.jsForce layouts, maps, data-bound transitions

For most explainer visuals, vanilla JS + CSS is sufficient.

Code Structure

Every visual is a self-contained HTML file:

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>Visual: [Concept Name]</title>
  <style>
    *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
    :root { /* Design tokens */ }
    /* Component styles */
  </style>
</head>
<body>
  <figure class="explainer-visual" role="img" aria-label="[Description]">
    <!-- Visual content -->
    <figcaption class="visually-hidden">[Accessible description]</figcaption>
  </figure>
  <script>
    // Animation and interaction logic
  </script>
</body>
</html>

Accessibility Requirements

.visually-hidden {
  position: absolute; width: 1px; height: 1px;
  padding: 0; margin: -1px; overflow: hidden;
  clip: rect(0, 0, 0, 0); border: 0;
}

@media (prefers-reduced-motion: reduce) {
  *, *::before, *::after {
    animation-duration: 0.01ms !important;
    transition-duration: 0.01ms !important;
  }
}

Every visual must include:

  1. role="img" aria-label="..." on container
  2. Full text alternative in .visually-hidden caption
  3. Respect prefers-reduced-motion
  4. Keyboard-accessible interactions
  5. Visible focus states

Patterns Reference

See references/patterns.md for implementation patterns:

  • Morphing shape transitions
  • Scroll-driven storytelling
  • Interactive slider diagrams
  • Annotated step-through animations
  • Force-directed relationship graphs
  • Unit/waffle chart animations

Delivery

Output as single HTML file that:

  1. Is completely self-contained (inline all CSS/JS)
  2. Works when opened directly in browser
  3. Can be embedded via iframe
  4. Includes comments explaining key decisions

For library-dependent visuals (D3, GSAP), include CDN links with integrity hashes.

Quality Checklist

Before delivering:

  • Static state communicates the core idea
  • Animation reveals insight, not just decorates
  • Interactions are discoverable (cursor hints, hover states)
  • Works on mobile (touch-friendly, responsive)
  • Reduced motion alternative exists
  • Accessible description is complete
  • Code is commented for future modification
  • File size reasonable (<100KB simple, <500KB complex)

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

37.23%
按下载量换算62

Claude

29.58%
按下载量换算49

Cursor

16.55%
按下载量换算27

Gemini CLI

9.28%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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