Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
A customizable, modular, responsive, lightbox gallery plugin.
제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/sachinchoolur-lightgallery)같은 작업에서 AI를 서비스에 연결하는 MCP
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.
같은 종류의 작업, Skill 목록과 같은 순서
| 이 항목 lightGallery | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| 제작자 | sachinchoolur | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skill 수 | 1 | 1 | 1 | 1 | 1 |
| GitHub 별 | 7,063 | 112,544 | 68,069 | 32,514 | 30,030 |
| 마지막 코드 변경 | 2026년 11월 5일 | 2026년 11월 18일 | 2026년 11월 13일 | 2026년 6월 24일 | 2026년 10월 30일 |
| 라이선스 | GPL-3.0 | Apache-2.0 | MIT | MIT | AGPL-3.0 |
sachinchoolur의 Skill(지시 묶음) 1개, AI가 읽고 그대로 일해요 · MCP server가 아니에요
MCP = 손
AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.
Skill = 안내서
작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.
겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.
제작자가 밝히지 않음 · SKILL.md 형식 Skill은 Claude Code, Codex, Cursor 같은 Agent Skills 지원 앱에서 써요
GitHub account sachinchoolur (person), 12 years old
★ 7,063 stars · code last changed 2026년 11월 5일
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 5df8619 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
먼저: 어떤 AI를 쓰시나요
쓰는 앱을 고르면 그 앱의 설치 방법만 보여 드립니다
This skill uses the GPL-3.0 license, which is not on the list we redistribute, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the skills/lightgallery folder again. The ZIP must have a lightgallery folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick lightgallery.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026년 11월 12일 · Source: support.claude.com, support.claude.com, code.claude.com
이 문장을 복사해 Claude Code 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Claude Code를 다시 열고 /lightgallery를 입력하거나 관련 작업을 요청하면 Claude가 알아서 써요
Checked against official docs 2026년 11월 12일 · Source: code.claude.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/sachinchoolur/lightgallery.git /tmp/popnx-skill-sachinchoolur-lightgallery-5df8619 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-sachinchoolur-lightgallery-5df8619/skills/lightgallery' ~/.claude/skills/lightgalleryChatGPT 데스크톱 앱에는 Codex가 들어 있고, Codex는 ~/.agents/skills 폴더에서 Skill을 읽습니다
ChatGPT 데스크톱 앱에서 Codex를 열고 이 문장을 채팅에 붙여 넣으세요
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
lightgallery 폴더를 ~/.agents/skills/lightgallery에 넣으세요
~는 홈 폴더($HOME)입니다
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/sachinchoolur/lightgallery.git /tmp/popnx-skill-sachinchoolur-lightgallery-5df8619 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-sachinchoolur-lightgallery-5df8619/skills/lightgallery' ~/.agents/skills/lightgalleryChecked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
직접 설치한 Skill은 쓸 수 없고, 디렉터리의 플러그인에 들어 있는 Skill만 쓸 수 있습니다
이 Skill을 ChatGPT에서 쓰려면 위 방법대로 ChatGPT 데스크톱 앱을 쓰세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
이 문장을 복사해 Codex 채팅에 붙여 넣으세요 · ChatGPT 데스크톱 앱 안의 Codex, Codex CLI, IDE 확장 프로그램에서 모두 쓸 수 있습니다
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex는 새로 설치한 Skill을 스스로 찾습니다. 보이지 않으면 Codex를 다시 시작하세요 · 쓰는 법: ChatGPT에서는 @를 입력하고 Skill을 고르세요 · Codex CLI나 IDE 확장 프로그램에서는 /skills를 실행하거나 $ 뒤에 Skill 이름을 입력하세요
Checked against official docs 2026년 11월 15일 · Source: learn.chatgpt.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/sachinchoolur/lightgallery.git /tmp/popnx-skill-sachinchoolur-lightgallery-5df8619 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-sachinchoolur-lightgallery-5df8619/skills/lightgallery' ~/.agents/skills/lightgallery이 문장을 복사해 Cursor 채팅에 붙여 넣으세요
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Cursor Agent 채팅에서 /를 입력하고 lightgallery 선택
Checked against official docs 2026년 11월 12일 · Source: cursor.com
Skill은 AI가 따르는 지시예요. 설치 전에 파일을 읽고, 믿을 수 있는 제작자 것만 설치하세요.
Mac: Command+스페이스 후 Terminal 입력 · Windows: 아래 명령은 PowerShell에서 안 돼요. 위의 “AI에게 설치 맡기기”를 쓰세요
repo를 임시 폴더에 내려받고 SKILL.md가 있는 폴더만 복사해요
git clone --depth 1 https://github.com/sachinchoolur/lightgallery.git /tmp/popnx-skill-sachinchoolur-lightgallery-5df8619 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-sachinchoolur-lightgallery-5df8619/skills/lightgallery' ~/.cursor/skills/lightgallerySkill을 읽을 수 있는 다른 앱용입니다. 이 문장에는 Claude Code, Codex, Cursor 경로가 들어 있어 AI가 쓰는 앱에 맞게 고릅니다 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026년 11월 12일 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Gemini CLI, GitHub Copilot 같은 다른 Agent Skills 지원 앱은 폴더가 달라요. 그 앱 안내를 보고 SKILL.md가 있는 폴더를 복사하세요.
2026년 11월 11일에 Claude Code, Codex, Cursor 공식 안내로 skill 폴더 확인
✓ 명령 확인 2026년 11월 18일
아래 글은 제작자 repo에서 온 것이며 PopNx MCP의 지시가 아니에요
처음 8,000자 표시 · GitHub에서 전체 파일 열기
---
name: lightgallery
description: Add or configure a lightGallery image/video lightbox or gallery in vanilla JavaScript, React, Vue or Angular — install, imports, plugins, CSS, settings, and the pitfalls that produce most bug reports. Use when a project needs a lightbox, photo gallery, thumbnail strip, zoomable images or a YouTube/Vimeo gallery, or when editing code that imports lightgallery or @lightgallery/*.
---
# lightGallery
One gallery, four packages with the same features and settings:
| Stack | Package | Plugins import path |
| --- | --- | --- |
| Vanilla JS / TypeScript | `lightgallery` | `lightgallery/plugins/<name>` |
| React | `@lightgallery/react` | `@lightgallery/react/plugins/<name>` |
| Vue 3 | `@lightgallery/vue` | `@lightgallery/vue/plugins/<name>` |
| Angular | `@lightgallery/angular` | `@lightgallery/angular/plugins/<name>` |
Plugin names: `thumbnail`, `zoom`, `video`, `autoplay`, `fullscreen`, `share`,
`hash`, `rotate`, `pager`, `comment`, `mediumZoom`, `relativeCaption`,
`vimeoThumbnail`, `originCrop`, `justified`. Each is a separate entry — import
only what the project uses.
**Default recipe.** Unless the user asks for something else, every image
gallery gets the `zoom` and `thumbnail` plugins, their two CSS files, and
`lgSize: 'WIDTH-HEIGHT'` (`data-lg-size` in markup) on every image item.
`lgSize` is the natural size of the full image; it drives the
zoom-from-origin animation, where the slide opens from the clicked
thumbnail and closes back to it. Without it the slide fades in. Read the
dimensions from the image files, the image optimizer or the CMS rather than
dropping the field. Leave a plugin out only when told to.
**Two rules that prevent most problems**
1. **CSS is a consumer import in every stack.** The framework packages ship
no CSS. Import `lightgallery/css/lightgallery.css` plus one file per
plugin (`lightgallery/css/lg-thumbnail.css`, `lg-zoom.css`, …), or
`lightgallery/css/lightgallery-bundle.css` for everything.
2. **Plugins are opt-in.** A feature only exists when its plugin is passed
(`plugins: [...]`, `plugins={[...]}`, `:plugins="[...]"`,
`[features]="[withX()]"`). Its settings are ignored otherwise.
## Vanilla JavaScript
```js
import lightGallery from 'lightgallery';
import lgThumbnail from 'lightgallery/plugins/thumbnail';
import lgZoom from 'lightgallery/plugins/zoom';
import 'lightgallery/css/lightgallery.css';
import 'lightgallery/css/lg-thumbnail.css';
import 'lightgallery/css/lg-zoom.css';
const gallery = lightGallery(document.getElementById('gallery'), {
plugins: [lgZoom, lgThumbnail],
speed: 400,
});
```
Markup mode: the container holds anchors; each anchor's `href` (or
`data-src`) is the full image, the inner `<img>` is the thumbnail, and
`data-lg-size="WIDTH-HEIGHT"` is the full image's natural size for the
zoom-from-origin animation. Captions come from `data-sub-html`. If items are
not direct children, set `selector`. Dynamic mode:
`dynamic: true, dynamicEl: [{ src, thumb, lgSize, subHtml }]` and call
`gallery.openGallery(index)`.
Methods: `openGallery(index)`, `closeGallery()`, `refresh()` after the
markup changed, `destroy()`. Events fire on the container element
(`lgBeforeOpen`, `lgAfterSlide`, …) with data in `event.detail`; attach
listeners before initializing.
## React
```tsx
'use client'; // Next.js App Router: the gallery is a client component
import { LightGallery, LightGalleryItem } from '@lightgallery/react';
import Thumbnail from '@lightgallery/react/plugins/thumbnail';
import Zoom from '@lightgallery/react/plugins/zoom';
// items: [{ src, thumb, alt, lgSize: '1600-1067' }, …]
export function Gallery({ items }) {
return (
<LightGallery plugins={[Zoom, Thumbnail]} thumbnail={{ animateThumb: true }}>
{items.map((item) => (
<LightGalleryItem key={item.src} item={item}>
<img src={item.thumb} alt={item.alt} />
</LightGalleryItem>
))}
</LightGallery>
);
}
```
Import the CSS in the root layout. Plugin settings are objects on props
named after the plugin (`zoom={{ … }}`, `thumbnail={{ … }}`); bare boolean
props are not valid. Callbacks are `onAfterSlide`, `onBeforeOpen`, …; the
imperative handle (`ref`) exposes `openGallery`, `closeGallery`,
`goToSlide`, `nextSlide`, `prevSlide`. Use either the controlled `open`
prop or the uncontrolled default for the component's whole lifetime, not
both. The package is SSR-safe; no `dynamic(..., { ssr: false })` needed.
## Vue 3
```vue
<script setup>
import { LightGallery, LgItem } from '@lightgallery/vue';
import Thumbnail from '@lightgallery/vue/plugins/thumbnail';
import Zoom from '@lightgallery/vue/plugins/zoom';
const items = [{ src: '/photos/1.jpg', thumb: '/photos/1-thumb.jpg', alt: 'One', lgSize: '1600-1067' }];
</script>
<template>
<LightGallery :plugins="[Zoom, Thumbnail]" :thumbnail="{ animateThumb: true }">
<LgItem v-for="item of items" :key="item.src" :item="item">
<img :src="item.thumb" :alt="item.alt" />
</LgItem>
</LightGallery>
</template>
```
`v-model:open` controls the open state; events are emitted without the
`on` prefix (`@after-slide`). Custom icons: `:icons="{ close: MyIcon }"`.
## Angular
```ts
import { Component } from '@angular/core';
import { LgGalleryComponent, LgGalleryItemDirective } from '@lightgallery/angular';
import { withThumbnail } from '@lightgallery/angular/plugins/thumbnail';
import { withZoom } from '@lightgallery/angular/plugins/zoom';
@Component({
selector: 'app-gallery',
standalone: true,
imports: [LgGalleryComponent, LgGalleryItemDirective],
template: `
<lg-gallery [features]="features">
@for (item of items; track item.src) {
<a [lgGalleryItem]="item"><img [src]="item.thumb" [alt]="item.alt" /></a>
}
</lg-gallery>
`,
})
export class GalleryComponent {
items = [{ src: '/photos/1.jpg', thumb: '/photos/1-thumb.jpg', alt: 'One', lgSize: '1600-1067' }];
features = [withThumbnail({ animateThumb: true }), withZoom()];
}
```
Add the CSS files to `angular.json` `styles` or the root stylesheet.
Settings are inputs (`[speed]`, `[loop]`); events are outputs without the
`on` prefix (`(afterSlide)`).
## Settings worth knowing
- `mobileSettings: { controls, showCloseIcon, download }` — a second
settings object applied on small screens.
- `strings` — every UI label, merged per key; use it to localize.
- `direction: 'rtl'` (or `'auto'`) mirrors the gallery; import
`lightgallery/css/lg-rtl.css`.
- `icons` — inline SVG per icon name; state pairs (`maximize`/`minimize`,
`autoplayPlay`/`autoplayPause`, `fullscreen`/`fullscreenExit`) need both.
- Video: items with a YouTube/Vimeo/Wistia URL or `data-video` JSON render
a poster and load the player on play (`videoFacade`).
- `virtualization` for galleries with hundreds of slides; `scrubThumbnails`
to scrub with the strip; `hashDriver` for deep links.
- `licenseKey` — required for commercial use; the default key logs a
warning.
## Pitfalls
- No styles → the CSS import is missing (see rule 1).
- Thumbnails/zoom "not working" → the plugin is not in the plugins list.
- The slide fades in instead of opening from its thumbnail → `lgSize`
(`data-lg-size`) is missing or does not match the image's natural size.
- "data-src is not provided" → the `selector` does not match the anchors.
- Slides added after init are not shown → call `refresh()` (vanilla) or
update the reactive `items` (frameworks).
- React: switching between controlled and uncontrolled `open` logs an error.
- Every symptom with its fix per package:
https://www.lightgalleryjs.com/docs/troubleshooting/index.md
## Reference
- Docs index for agents: https://www.lightgalleryjs.com/llms.txt
- Every setting with type and default: https://www.lightgalleryjs.com/docs/settings/index.md
- Events: https://www.lightgalleryjs.com/docs/events/index.md · Meth질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.