Token导航 LogoToken导航TokenDH.com
前端设计操作浏览器github未标认证来源可访问许可证需确认审计提醒

visualizevisualize 前端

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

198

周安装

8

GitHub Stars

公开资料未说明

下载量

62
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:visualize(visualize 前端)
来源仓库:https://github.com/abpai/skills
仓库路径:skills/visualize
安装命令:
npx skills add https://github.com/abpai/skills --skill visualize
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/abpai/skills --skill visualize

简介

用于生成自包含的 HTML 文件,以可视化方式解释系统、流程或概念。

  • 适合在复杂计划、代码流或第三方内容理解时提供直观展示。
  • 输出直接打开浏览器预览,避免使用 ASCII 图表替代。
  • 安装需通过 npx 添加 GitHub 仓库,使用前应熟悉 base.html 模板和格式指南。
  • visualize 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Visualize

Generate a single, self-contained HTML file that visually explains a system, plan, code flow, or concept. The output opens in the browser — never fall back to ASCII art when this skill is loaded.

When to Use

  • Visualize a complicated plan or proposal
  • Explain key primitives before implementing a plan
  • Visual explanation of steps from a third-party repo or blog post
  • Understand a module's code flow or execution path

Workflow

  1. Understand what the user wants to see — the subject, the audience, the level of detail.
  2. Read ./templates/base.html to absorb the tech stack and Threaded style. Read it each time, do not rely on memory.
  3. Pick the format (see Format Guide below).
  4. For Mermaid diagrams with 10+ nodes, also read ./references/mermaid-tips.md.
  5. Adapt the base template for this specific visualization. Reuse the structure, swap the visual area content.
  6. Write to ~/.agent/diagrams/<descriptive-name>.html and open in the browser.

Format Guide

IntentApproach
Flows, processes, sequencesMermaid.js in the visual area
Architecture, system overviewMermaid.js or CSS Grid cards
Comparisons, dataHTML <table>
Step-by-step conceptsWalkthrough (base template pattern)
Timelines, roadmapsCSS timeline in the visual area

Tech Stack

Every generated file uses:

  • Preact + htm — ESM CDN imports, no build step
  • Tailwind CSS CDN — utility classes with inline config
  • Google Fonts — Merriweather (serif) + Inter (sans)
  • Mermaid.js CDN — add only when diagrams are needed

No other dependencies. No build step.

For the full Threaded design tokens (colors, typography, motion), see ./references/design-system.md.

Principles

  • One primary visual anchor per request, plus supporting evidence visuals when reviewing a plan or system
  • Visual first — the main content is a diagram, chart, or table, not prose
  • Adapt the base template — don't start from scratch
  • Correct over pretty — the visualization must accurately represent the information
  • Interactive when it helps comprehension (step-through, hover, collapse)
  • Never use innerHTML with user-provided content (XSS prevention)

Avoiding Escaped Backticks in Output

The Write tool can corrupt JavaScript template literals, writing literal `` \ and `${ instead of real backticks and interpolations. This breaks all htm tagged templates. To prevent it:

  1. Extract data into separate const variables above the htm templates. Mermaid chart definition strings, config arrays, long text — declare them as plain constants first, then reference the variable inside html\...``.
  2. Keep htm expressions simple. Pass variables by reference (${myVar}, ${myArray.map(...)}). Do not build complex multi-line strings or nested template literals inline within an html\...`` block.
  3. Verify after writing. Re-read the first 30 lines of the <script type="module"> block in the written file and confirm there are no escaped sequences (`` \ or `${). If Chrome DevTools MCP is available, check the browser console forSyntaxError after opening the file.

Before Delivering

  • First screen test: is a meaningful visual visible without scrolling?
  • File opens cleanly: no console errors, no broken fonts?

Output

Write to ~/.agent/diagrams/ with a descriptive filename (auth-flow.html, pipeline-overview.html).

Open in browser:

  • macOS: open ~/.agent/diagrams/filename.html
  • Linux: xdg-open ~/.agent/diagrams/filename.html

Tell the user the file path and name the visuals you included.

Update Check

On first use in a session, silently check for a newer version:

  1. Fetch https://raw.githubusercontent.com/abpai/skills/main/versions.json.
  2. Compare the version for visualize against this file's metadata.version.
  3. If the remote version is newer, pause before the main task and ask: visualize update available (local {X.Y} → remote {A.B}). Would you like me to update it for you first? I can run npx skills update visualize for you.
  4. If the user says yes, run the update before continuing.
  5. If the user says no, continue with the current local version.
  6. If the fetch fails or web access is unavailable, skip silently.

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

36.21%
按下载量换算22

Claude

29.95%
按下载量换算19

Cursor

17.94%
按下载量换算11

Gemini CLI

8.91%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

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