What it does
中文手绘技术 PPT 整页图像生成 Skill | 21:9 封面 + 16:9 正文配图 | PNG 输出
- Connects Instruction files the AI reads
- Account or key No key found in README or SKILL.md
- Category 自动化与智能体
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/helloianneo-ian-handdrawn-ppt)相似的 Skill
同类工作,排序与 Skill 列表相同
Skill 和 MCP 有什么不同
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
适用的应用
Claude CodeCodex
依据开发者 README 和 repo 中的文件夹
安装
Is it safe?
- Who made it
GitHub account helloianneo (person), 5 years old
- Use and upkeep
★ 1,526 stars · code last changed 2026年10月27日
- Any scripts?
No, plain text files the AI reads and follows
- Uses the internet?
No scripts, so it does not go online by itself
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 7b832a4 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (553). Use "Let the AI install it" instead
Option 1让 Claude Code 帮你安装
复制这句话,粘贴到 Claude Code 的对话中
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
重新打开 Claude Code,输入 /ian-handdrawn-ppt,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.claude/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/helloianneo/ian-handdrawn-ppt.git /tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4/ian-handdrawn-ppt' ~/.claude/skills/ian-handdrawn-ppt重新打开 Claude Code,输入 /ian-handdrawn-ppt,或直接提出相关任务,Claude 会自动选用
ChatGPT 桌面应用
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
Option 1让 ChatGPT 帮你安装
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
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
Option 2自己放入文件夹
把 ian-handdrawn-ppt 文件夹放到 ~/.agents/skills/ian-handdrawn-ppt
~ 是你的主文件夹($HOME)
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/helloianneo/ian-handdrawn-ppt.git /tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4/ian-handdrawn-ppt' ~/.agents/skills/ian-handdrawn-ppt
安装之后
- ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
- 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
- Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
网页版和手机版 ChatGPT
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Option 1让 Codex 帮你安装
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
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
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.agents/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/helloianneo/ian-handdrawn-ppt.git /tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4/ian-handdrawn-ppt' ~/.agents/skills/ian-handdrawn-ppt重新打开 Codex 并提出相关任务,Codex 会列出这个 skill
Option 1让 Cursor 帮你安装
复制这句话,粘贴到 Cursor 的对话中
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
在 Cursor 的 Agent 聊天中输入 / 并选择 ian-handdrawn-ppt
Checked against official docs 2026年11月12日 · Source: cursor.com
For Terminal users
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
打开终端
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
把 skill 文件夹复制到 ~/.cursor/skills
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/helloianneo/ian-handdrawn-ppt.git /tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-helloianneo-ian-handdrawn-ppt-7b832a4/ian-handdrawn-ppt' ~/.cursor/skills/ian-handdrawn-ppt在 Cursor 的 Agent 聊天中输入 / 并选择 ian-handdrawn-ppt
Option 1Let the AI install it
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · 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 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月18日
查看原始 SKILL.md
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: ian-handdrawn-ppt
description: Create final Chinese handdrawn technical article/PPT-style page images from articles, Markdown, PDFs, DOCX files, existing slide decks, course notes, scripts, outlines, or rough ideas. Use when the user asks to turn content into PPT/PPTX/slides/courseware/课件/演示稿/配图/效果图 in a refined Chinese handdrawn technical explanation style, to plan such pages, to choose page layouts from semantic content, or to generate complete image-model pages with Chinese text baked into the final visual. Default article outputs use 21:9 covers and 16:9 body illustrations.
---
# Ian Handdrawn PPT
Turn source material into a Chinese handdrawn technical PPT-style image deck. Optimize for commercial delivery: clear narrative, semantic page archetypes, exact short Chinese text, refined handdrawn diagrams, and deck-level visual consistency.
## Operating Rule
Default production output is complete raster page images generated by the built-in image generation model. Blog/article covers default to 21:9; body illustrations and standard deck pages default to 16:9. Each page is a final visual deliverable with both diagram and Chinese text included in the image.
In this skill, "PPT", "slides", "page", and "deck" mean finished PPT-style visual page images, not editable presentation/document files. Do not route to presentation or document packaging merely because the user says PPT/PPTX/PDF. Editable PPTX, image-based PPTX, and PDF export are out of scope for this skill.
Do not use deterministic drawing scripts, HTML, SVG, canvas, or python-pptx as the primary visual generator for style samples. Deterministic post-processing is allowed for crop/resize, contact sheets, or exact text overlay when the generated image direction is accepted but image text fidelity is not good enough.
Produce a planning blueprint when the user asks to plan, outline, or design first. Production output is final PNG page images plus a contact sheet when there are multiple pages.
## Resource Map
Load only the references needed for the current task:
- `references/intake.md`: input types, missing-information checks, and concise clarification rules.
- `references/narrative-planning.md`: deck type selection and story structures.
- `references/slide-archetypes.md`: semantic mapping from content type to slide layout.
- `references/visual-dna-v6.md`: handdrawn Chinese technical PPT visual system and deck-level style lock.
- `references/output-quality.md`: output contracts and verification gates for final image pages.
- `references/prompt-patterns.md`: prompt templates for complete image-model slide pages.
Use `assets/theme-tokens.json` as the compact theme token file when writing prompts.
Use `assets/reference-handdrawn-article-illustration-style.png` as the active style anchor for blog/article cover and body illustrations.
When the current image tool supports local reference images, load or attach this style anchor before generation. When it does not, use the theme tokens plus the reference-match clause in `references/prompt-patterns.md`, and report the style as prompt-matched rather than image-referenced.
Do not use legacy bordered PPT reference images unless the user explicitly asks to recreate the older bordered look.
## Workflow
1. **Ingest material**
- Read the provided content or attached file.
- If the input is `.pptx`, extract the source content and visual intent only; do not edit or package the PPTX inside this skill.
- If the input is `.docx`, use the Documents plugin or skill to extract content.
- If the input is `.pdf`, use the PDF/document tooling appropriate to the task.
- If the input is plain text, Markdown, notes, or an outline, parse it directly.
2. **Run intake and gap diagnosis**
- Read `references/intake.md` when the content is broad, incomplete, or the output requirements are unclear.
- Determine topic, audience, scenario, target length, and source sufficiency.
- Ask at most 1-3 questions only when the missing information materially changes the deck.
- If no critical information is missing, proceed with reasonable defaults.
3. **Plan the deck narrative**
- Read `references/narrative-planning.md`.
- Classify the deck as teaching, persuasive, report, product explanation, or knowledge-card style.
- Create a slide-by-slide spine: each slide must have one main point.
4. **Map each slide to an archetype**
- Read `references/slide-archetypes.md`.
- Choose slide layouts from the content semantics, not from a fixed template order.
- Vary archetypes so the deck has rhythm.
5. **Apply visual DNA**
- Read `references/visual-dna-v6.md`.
- Use small exact Chinese text, fine handdrawn lines, light pastel marks, few characters, low visual heaviness, large negative space, and one shared master layout language across the whole deck.
- Lock cross-page constants before generating: page role, canvas ratio, near-white paper tone, no-border default, page number, title treatment, title optical size, line weight, pastel palette, corner grid marks, character policy, and spacing rhythm.
- Keep the outer shell fixed across pages: page number location, title block, underline, paper tone, corner marks, and visual scale. Vary only the middle semantic diagram area according to the content.
- Treat blog/article visuals as two role-specific outputs by default: a 21:9 cover image and 16:9 body illustrations. Do not let body pages look like cover pages.
6. **Build output**
- For planning-only requests, deliver a structured blueprint with deck type, slide count, title, main point, archetype, content blocks, visual brief, and missing inputs.
- For production requests, use the built-in image generation model to generate one complete page image per slide/visual. Use one image generation call per distinct page brief, not a generic repeated template.
- When the user asks for a cover plus body illustrations, generate the cover as 21:9 and body illustrations as 16:9 unless the user specifies otherwise.
- Before generating multiple pages, write one compact deck style lock and reuse it verbatim in every page prompt. Add page-specific layout instructions only for the central diagram/content area.
- Keep all visible Chinese text short and exact in the prompt. Include a `Required text only` list for each page.
- If exact Chinese text is mission-critical or repeated generations render text incorrectly, reduce the text budget first. If needed, generate the accepted visual with blank label spaces and add exact text as deterministic post-processing; the final deliverable is still a raster page image.
- Save final selected images into the workspace, and make a contact sheet when generating multiple pages.
- Check actual image dimensions. If the image model returns near-target native sizes, report the actual size; normalize body illustrations to 1920x1080 and cover images to 2520x1080 only when strict delivery dimensions are requested.
7. **Verify**
- Read `references/output-quality.md`.
- Check content accuracy, slide rhythm, Chinese text accuracy, visual consistency, style-anchor match, and commercial handoff readiness.
- If verification fails, revise before final delivery.
## Defaults
Use these defaults unless the user says otherwise:
- Language: Simplified Chinese.
- Audience: Chinese learners with some technical curiosity but not necessarily expert depth.
- Deck length: 8-12 slides for an article, 15-30 slides for a course module, 5-8 slides for a short idea.
- Output: final PNG page images plus a contact sheet and short slide blueprint summary.
- Blog/article visual split: cover image is 21:9; body illustrations are 16:9.
- Style: refined near-white Chinese handdrawn technical article/PPT illustration V6.
## Final Response
When finished, report:
- The created image folder and contact sheet path.
- The page count and deck type.
- Any important assumptions.
- Verification performed and any rema讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
来自 GitHub
- GitHub 星标
- 1,526
- 开发者
- helloianneo
- 许可证
- MIT
- 最近代码更新
- 2026年10月27日
- repo 中的 SKILL.md 文件(含译本和模板)
- 1
- 主题
- ai-agent, chinese, codex-skill, handdrawn, image-generation, ppt