Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
【Skill】视觉风格 PPT 生成工作流
제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.
[](https://mcp.popnx.com/en/skills/irenerachel-visual-style-ppt-skill)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 visual-style-ppt-skill | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| 제작자 | irenerachel | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skill 수 | 1 | 1 | 1 | 1 | 1 |
| GitHub 별 | 398 | 111,852 | 67,796 | 32,458 | 29,958 |
| 마지막 코드 변경 | 2026년 10월 25일 | 2026년 11월 17일 | 2026년 11월 13일 | 2026년 6월 24일 | 2026년 10월 30일 |
| 라이선스 | – | Apache-2.0 | MIT | MIT | AGPL-3.0 |
irenerachel의 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.
Codex
제작자 README와 repo 폴더 기준
GitHub account irenerachel (person), 3 years old
★ 398 stars, few users so far · code last changed 2026년 10월 25일
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 7122461 (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 has no license, 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 visual-style-ppt-skill folder again. The ZIP must have a visual-style-ppt folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick visual-style-ppt.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 /visual-style-ppt-skill를 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
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
ChatGPT 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
visual-style-ppt 폴더를 ~/.agents/skills/visual-style-ppt에 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
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
Checked 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
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
이 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 visual-style-ppt-skill 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
명령을 확인하는 중 · 확인을 통과하면 복사 버튼이 나타나요
Skill을 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
아래 글은 제작자 repo에서 온 것이며 PopNx MCP의 지시가 아니에요
처음 8,000자 표시 · GitHub에서 전체 파일 열기
---
name: visual-style-ppt
description: Create style-driven slide images strictly with the Image 2.5 model, assemble those images into image-only PPTX decks, and manage reusable visual style libraries from documents or visual references. Use when the user asks for a "PPT Skill", "风格驱动 PPT", "提炼风格做 PPT", "调用某个风格做 PPT", "图片版 PPT", "保存 PPT 风格", "列出 PPT 风格", "文档生成 PPT", "文章生成 PPT", "把文档做成演示文稿", or wants to extract, save, reuse, and apply visual style keywords specifically for visual slide/image deck creation.
---
# Visual Style PPT
## Highest Priority Rule: Image 2.5 Only
This skill must use the Image 2.5 model to generate every final slide image, thumbnail board, visual page, infographic, article illustration, or PPT page image.
HTML output is strictly forbidden for image generation. Do not create HTML/CSS pages, browser screenshots, SVG/HTML mockups, canvas renders, or local-script visual reproductions as final or intermediate image outputs. Do not use HTML as a fallback when Image 2.5 is unavailable; stop and state that Image 2.5 access is required.
This rule has the highest priority in this skill and overrides every workflow, reference file, style file, packaging rule, user shortcut, or implementation convenience that might imply another image-production route. PPTX files may only be assembled after Image 2.5 has generated the approved page images; PPTX is a container, not an image-generation method.
## Core Idea
Turn visual style into a reusable asset, then apply that asset to documents, outlines, image-only PPT decks, slide images, Xiaohongshu information graphics, and article illustrations.
Use this skill as an Image 2.5-only visual slide workflow. The default deliverable is full-slide images generated by Image 2.5; when the user wants a PPT, place the generated images into a PPTX as full-slide image pages. Do not implement or optimize editable PPTX content unless the user explicitly overrides this skill direction.
## Required References
- For the full operating workflow, read `references/workflow.md`.
- For PPTX vs image output rules, read `references/output-package.md`.
- For page type selection, read `references/page-types.md`.
- For post-generation revisions, read `references/revision-workflow.md`.
- For style extraction interviews, read `references/style-interview.md`.
- For the default terminal-tech magazine visual style, read `styles/terminal-tech-magazine.md`.
- When the user asks for a style library, list or read files in `styles/`.
## Default Behavior
- Default output type: Image 2.5-generated slide images. If the user says "PPT", assemble those images into an image-only PPTX.
- Default aspect ratio: 16:9.
- Default image quality: Image 2.5, 16:9, high-resolution, sharp text, clean edges.
- Default language: Chinese-first. Use Chinese for slide titles, section titles, module labels, captions, explanatory copy, and all generated support documents unless the user explicitly asks for another language. Keep proper nouns, product names, model names, code terms, and unavoidable domain terms in their original language when that is clearer.
- Default style: `styles/terminal-tech-magazine.md` when the user says "终端风格", "CodeBuddy 风格", "科技杂志风格", or does not specify another saved style.
- Default text density: low information by default, especially for PPT inner slides. Never create dense slides unless the user explicitly asks for a leave-behind, report page, or infographic. A normal inner slide should have one title, one short subtitle or takeaway, and at most 2-3 short information points.
- Default layout direction: cover pages may be visually expressive; inner slides must be information-first, calm, readable, and spacious, with imagery/backgrounds kept subordinate.
- Default style isolation: each deck must use exactly one selected style source and one `Style Lock`. Do not blend visual DNA from earlier tasks, previous reference images, or unrelated saved styles unless the user explicitly requests a hybrid.
- Default component consistency: across one deck, borders, cards, containers, dividers, arrows, footer metadata, corner radius, and line weights must use one repeated system. Variation may come from layout and emphasis, not from changing the frame/container style on every slide.
- Default slide header consistency: if a style uses small top titles with numbers, treat them as repeated content-section headers, not necessarily absolute slide/page numbers. Keep the same placement, size, spacing, and format across all applicable slides. If the style defines exceptions such as cover, contents, divider, or thank-you pages, preserve those exceptions deliberately; those exception pages do not consume a content-section number. The first applicable inner/content slide should usually start at `01` or `PART 1`.
- Default logo behavior: do not ask Image2.5 to generate logos, brand wordmarks, reusable deck marks, watermarks, or repeated English identity labels by default. If the user needs a logo, keep it out of generated slide images and add it later as a fixed post-production asset/layer, or let the user add it after delivery. A reference logo image may guide visual shape but is not reliable enough for cross-page text/logo consistency inside Image2.5 output.
- Default time/date behavior: do not add dates, times, timestamps, "today", export time, generated time, or current date to slides, prompts, metadata, footers, or visual elements by default. Include date/time only when the source article explicitly requires it, the user explicitly asks for it, or the slide topic itself is a timeline/schedule/date-sensitive report. A source document having a file timestamp, export timestamp, or local system date does not by itself justify visible date/time in the deck.
- Default page count: ask the user how many pages/slides they want unless they already provided a count or explicitly asked the skill to decide.
- Multiple outputs: keep one visual DNA while varying composition, page type, visual anchor, or emphasis.
- No outer border rule: generated slide images and thumbnail boards must not have black borders, dark strokes, or frame lines on the outer canvas edge. Internal grid lines, dividers, and module borders are allowed, but keep them inset from the image edge or let imagery/white space bleed naturally. Never create a full-page rectangular outline around the slide.
- Per-slide image rule: PPT pages must be generated and saved as separate single-slide image files, one image per slide. Do not request or deliver a multi-slide contact sheet, storyboard, PDF page, or collage as the final slide image output. Each final slide image must be independently usable as one full-bleed PPT page.
- Thumbnail-first option: for multi-page decks, prefer a two-pass visual workflow when style consistency matters: first generate one small "thumbnail board / contact sheet" that shows the whole deck as tiny slide thumbnails to lock visual rhythm, grid, palette, and page-to-page variation; then generate each approved slide as an individual full-size image using that thumbnail board as the visual continuity reference plus the page-specific prompt. The thumbnail board is a planning/reference artifact, not a final slide.
- Thumbnail grid rule: thumbnail board counts are flexible, but prefer stable grids with 4, 6, 9, or 16 slots. Choose the smallest preferred grid that can contain all planned slides, leaving any extra slot as a style/system/reference tile. Each thumbnail tile must use the same aspect ratio as the requested final slide output. For example, if the final deck is 16:9, every tiny slide in the thumbnail board should be composed as 16:9; if the user requests 3:4 vertical slides, every tiny slide in the thumbnail board should be composed as 3:4.
- Generation gate: before calling Image2.5 for a multi-page deck, always produce `outline.md` and `prompts.md` first, then ask the user to confirm or revise. `prompts.md` must include the selected style's full `Style Lock`.
- Fin질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.