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 Automation and agents
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/helloianneo-ian-handdrawn-ppt)Similar Skills
Same kind of work, ordered like the Skills list
1 skills (instruction sets) by helloianneo that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodex
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account helloianneo (person), 5 years old
- Use and upkeep
★ 1,526 stars · code last changed Oct 27, 2026
- 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
First: which AI do you use?
Pick your app and this page shows only how to install it there
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 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code 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
Restart Claude Code, then type /ian-handdrawn-ppt or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
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-pptRestart Claude Code, then type /ian-handdrawn-ppt or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
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 2Put the folder there yourself
Put the ian-handdrawn-ppt folder at ~/.agents/skills/ian-handdrawn-ppt
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
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
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
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 picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
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-pptRestart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor 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
In Cursor’s Agent chat, type / and pick ian-handdrawn-ppt
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
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-pptIn Cursor’s Agent chat, type / and pick ian-handdrawn-ppt
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · 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 Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
✓ Commands checked Nov 18, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
Showing the first 8,000 characters · Open the full file on GitHub
---
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 remaDiscussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 1,526
- Maker
- helloianneo
- License
- MIT
- Last code change
- Oct 27, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 1
- Topics
- ai-agent, chinese, codex-skill, handdrawn, image-generation, ppt