Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/op7418-guizang-yingzao-skill)MCP servers that connect the AI to services for the same work
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.
Same kind of work, ordered like the Skills list
| This one guizang-yingzao-skill | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| Maker | op7418 | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 539 | 113,042 | 68,296 | 32,579 | 30,091 |
| Last code change | Sep 3, 2026 | Nov 19, 2026 | Nov 19, 2026 | Jun 24, 2026 | Oct 30, 2026 |
| License | – | Apache-2.0 | MIT | MIT | AGPL-3.0 |
1 skills (instruction sets) by op7418 that an AI reads and follows · not an MCP server
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.
Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor
GitHub account op7418 (person), 11 years old
★ 539 stars · code last changed Sep 3, 2026
14 scripts that can run on a computer: scripts/make_comparison.py, scripts/_runtime.py, scripts/check_dependencies.py, scripts/design_tokens.py and 10 more
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 58c9b87 (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
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 yingzao folder again. The ZIP must have a yingzao folder with SKILL.md at the top level, no loose files
+Create skillUpload a skillpick yingzao.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 Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
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 /yingzao or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Already installed? Check first · Open Terminal, type this command and press Enter
node -vMac: press ⌘ + Space, type Terminal, press Enter
Windows: open Start, type Windows PowerShell, then Open
Not installed: Open the official download page, pick the LTS version and the click-through installer: .pkg on Mac · .msi on Windows. Double-click and follow it to the end. No curl command needed
Open the Node.js download page ↗
When it’s done, close Terminal, open it again and run the same command. You should see a version number: node -v
Install once; it works for everything that needs Node.js
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
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
Put the yingzao folder at ~/.agents/skills/yingzao
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
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
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
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
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 yingzao
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
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
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
The text below comes from the maker’s repo, not from PopNx MCP
4,446 characters · Open the full file on GitHub
---
name: yingzao
description: Transform real Chinese architecture and place-based cultural photos into art-directed editorial posters, integrated multi-photo scenes, and optional source comparisons. Use for historic buildings, vernacular streets, culturally rooted shops, interiors, food, travel covers, and place montages; do not use for generic advertising, routine retouching, or invented places.
---
# Yingzao · 营造
把真实建筑与在地文化照片转译为有主体处理、主动背景、字形设计和空间互动的编辑海报。先从照片提出创意命题,再让一张兼容的主导参考强化它;Token 负责检索与机制追踪,不能替代设计判断。
## 核心合同
- 高风格化任务固定使用:Image 1 校正原图、Image 2 一张主导参考实图、Image 3 稀疏中性排版垫图。生成前必须由 `scripts/prepare_generation.py` 编译成一次调用清单,不得互相替代、改序或在调用时重新概括提示词。
- 所选 Recipe 必须保存为 `analysis/recipe.json`,再把全部启用 Token 编入 `analysis/design-plan.json`:除确定性校正项外,每个 Token 都要归入主体、背景、字体或互动动作,并指向 Image 3 中同名的区域标记。编译器把这些动作写入最终模型提示词;只在简报里出现、不进入提示词和垫图的 Token 视为未投递。
- 创意命题必须先于参考检索,并同时说明:`主体如何处理 / 背景如何主动参与 / 文字如何与真实轮廓互动 / 哪个非默认排版动作打破双居中`。
- `reinterpret` 展示字在首次生成前完成 `glyph-brief.md` 和逐字光学补偿,并在垫图使用 `guide_render: scaffold`,避免普通字体轮廓压过字形说明;不能只写宋体、黑体、衬线或“高级复古”。资料小字可使用另一常规字族。
- 图像模型必须完成语义抠取、构图修复、共同重光、背景重建、区域材质、图文遮挡等代码不能替代的动作。普通裁图、滤镜、渐变和打字能复现的方案无效。
- 单图的主体域、背景域、互动域都要在缩略尺度可见。主体居中、标题居中且互不接触的“两座孤岛”默认无效。
- 提示词只表达一个艺术方向,不拼接 Token 约束、失败案例或长验收清单。
- 只生成用户要求的数量。成图后必须读回一次并简要指出明显问题,但不自动评分、制作 proof 或重生成;用户反馈后才定向修改。
## 输入确认
从用户消息提取:地点/对象与必要文案、海报数量、是否要原图对照拼图。已明确的不再问;用户说“你决定”时默认 1 张、只用已确认或可核实短词、不生成对照拼图。名称不确定时可识别或检索,不能凭外观编造。
## 工作流
### 0. 建立安全输入
1. 运行 `python3 scripts/check_dependencies.py`。入口会自动寻找调用者目录中的兼容 `.venv`;失败时停止并说明,不全局安装,也不静默降级。
2. 产物写入调用者工作目录的 `output/yingzao/<run-id>/`,不得写入 Skill 包。
3. 每张来源运行 `scripts/photo_preflight.py`,判定 `hero / support / reject`,记录照片轴和构图问题。需要时先用 `scripts/rectify.py` 做确定性校正。
4. 事实按 `VERIFIED / OBSERVED / USER-CONFIRMED / UNCONFIRMED` 分级;只有前三类进入海报。细则见 [photo-preflight.md](references/photo-preflight.md) 与 [research-and-annotation.md](references/research-and-annotation.md)。
### 1. 冻结创意命题并选择参考
先写四域命题,再从 preflight 的受控标签检索:
```bash
python3 scripts/design_tokens.py suggest \
--tag <标签> --count <数量+1> --maximize-distance \
--history output/yingzao/<run-id>/recipe-history.json \
--record-history
python3 scripts/design_tokens.py recipe <id> --json \
> output/yingzao/<run-id>/analysis/recipe.json
```
零命中返回状态 2,此时换受控词重查。用 `recipe <id> --json` 取得真实 `reference_assets`,并将完整输出保存为 `analysis/recipe.json`;高风格化任务恰好选择一张主导参考。它必须与目标的主体占幅、负空间拓扑和互动边界兼容,并实际示范主体处理、主动背景和图文关系。选择方法见 [mixing-logic.md](references/mixing-logic.md)。
把会改变生成决策的内容写入 [creative-brief.md](references/creative-brief.md),再通过 [preflight-gates.md](references/preflight-gates.md) 的八个生成前门控。
### 2. 设计字形与空间关系
按 [frontend-layout-guide.md](references/frontend-layout-guide.md) 用 `scripts/typeset_compose.py` 生成中性稀疏垫图。先写 `design-plan.json`,把四域动作分别标为 `S1 / B1 / T1 / I1` 等;对应标题层、主体轮廓和背景区域必须使用 `guide_marker + guide_label` 标在垫图上。展示层必须显式声明 `glyph_design_mode`;`reinterpret` 只画字符槽与小型字面标签,不把普通字体的大轮廓喂成最终形制。垫图只锁必要文字、层级、共同轴、阅读顺序、动作区域和主要遮挡,不锁最终颜色、材质或网页式容器。
展示标题为 `reinterpret` 时,按 [display-glyph-morphology.md](references/display-glyph-morphology.md) 保存 `analysis/glyph-brief.md`:选择一个字形谱系,记录至少五项可见特征,并逐字说明光学问题、轮廓动作和不可改变的标准部件。若声明主体压字,垫图必须用 Image 1 的真实轮廓建立 `subject-footprint` 和遮挡契约。
### 3. 整体生成
单图和同址多图融合默认使用 edit。先按 [image-generation-workflow.md](references/image-generation-workflow.md) 写提示词并运行 `scripts/prepare_generation.py`;只有脚本返回 `READY` 才能调用图像模型。调用时原样使用清单中的 `tool_arguments`,不得省略主导参考、垫图或主体/背景/互动段。
多图“合一”时逐图提取主体,重组进共享透视、光向、接触阴影、边缘语言和材质的同一环境;只有用户明确要求组照或对照时才保留照片矩形。
### 4. 交付与按需扩展
- 生成后先用读图工具打开成图,按 [image-generation-workflow.md](references/image-generation-workflow.md) 做一次五项快速读回,把最明显的 0–3 个问题写入 `analysis/readback.md`;不因此自动重生成。
- 用户不要拼图:交付海报。用户要对照:运行 `scripts/make_comparison.py ORIGINAL POSTER OUTPUT`。
- 邀请用户指出字体、主体处理、构图、材质、文案或融合关系中的具体修改。收到反馈后,局部问题以当前成图为 edit target;主体、背景、主布局、参考方向或图文关系等结构问题回到校正原图,重做命题、参考和垫图。
- 海报交付后问一次:“要不要继续把这张海报扩展成一张 3×3 视频分镜图,并附一段可直接交给视频模型的提示词?”用户同意后才读取 [video-storyboard.md](references/video-storyboard.md);不要自动生成视频。
## 按需参考
| 情况 | 文件 |
| --- | --- |
| 需要具体字体、构图、材质或文化转译方法 | [art-direction.md](references/art-direction.md) |
| 制作排版垫图 | [frontend-layout-guide.md](references/frontend-layout-guide.md) |
| 设计展示字形 | [display-glyph-morphology.md](references/display-glyph-morphology.md) |
| 维护 Recipe / Token | [token-system.md](references/token-system.md) |
| 读取所选参考的编码 | [reference-encoding-matrix.md](references/reference-encoding-matrix.md)、[reference-encoding-expansion-2026.md](references/reference-encoding-expansion-2026.md);只读命中的条目 |
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.