Skip to content
Skills Library
Marketing & content · Building & coding

ui-image-generation

/ui-image-generation

Generate or edit raster images and visual assets, including UI and prototype visuals, website images, illustrations, icons, placeholders, reference images, banners, covers, or image variants. Trigger for Image Gen, AI image generation, UI assets, concept visuals, bitmap generation, or visual assets.

Repository
axhub-make ↗
Licence
Apache-2.0
Last repository change
03.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/request-image.mjs

What it does and when to use it

Generate or edit raster images and visual assets, including UI and prototype visuals, website images, illustrations, icons, placeholders, reference images, banners, covers, or image variants. Trigger for Image Gen, AI image generation, UI assets, concept visuals, bitmap generation, or visual assets.

Original author description

Generate or edit raster images and visual assets, including UI and prototype visuals, website images, illustrations, icons, placeholders, reference images, banners, covers, or image variants. Trigger for Image Gen, AI image generation, UI assets, concept visuals, bitmap generation, or visual assets.

How it works

  1. 工作流
  2. 设备与画布比例
Original SKILL.md headings · 52 lines, 259 words
SKILL.md preview
---
name: ui-image-generation
description: Generate or edit raster images and visual assets, including UI and prototype visuals, website images, illustrations, icons, placeholders, reference images, banners, covers, or image variants. Trigger for Image Gen, AI image generation, UI assets, concept visuals, bitmap generation, or visual assets.
---

# 项目图片生成

这是 Axhub Make client 对系统 `imagegen` 能力的项目入口。当前项目需要新生成、编辑或派生位图图片/视觉素材时,先使用本技能;系统 `imagegen` 规则作为下游通用规范,不绕过本技能的工具与配置选择。

## 工作流

1. 如果当前环境提供内部图片生成 MCP 或图片生成工具,优先使用。
2. 内部图片生成工具不可用时,通过 Axhub Make 服务端图片代理生成;不得读取 `server.config.json` 或 `server.secrets.json` 获取供应商配置或凭据。
3. Make 服务运行且图片配置完整时,执行本技能内置的 `scripts/request-image.mjs`:
   - 将最终提示词写入项目 `.local/` 下的临时文本文件。
   - 单张请求使用:`node "<当前技能目录>/scripts/request-image.mjs" --project-id "<当前项目 ID>" --prompt-file "<提示词文件>" --out "<输出图片>" --size "<WxH>" --quality "<auto|low|medium|high>"`。
   - 有参考图时重复追加 `--image "<本地图片路径>"`;脚本只负责把参考图随生成请求上传,不处理 mask、抠图、缩放或其他本地图片编辑。
   - 脚本从 `.admin-server-info.json` 发现已运行的 Make 服务,并调用项目作用域的 `/api/ai/image/generate`;供应商凭据始终留在 Make 服务端。
   - 不要先检查或安装 Python、`uv`、OpenAI SDK 或 npm 依赖,也不要临时编写其他 API runner。
4. Make 服务不可用或图片配置不完整时,不读取其他本地认证文件;报告原因并回退到系统 `imagegen` 的默认行为。
5. Make 图片配置完整时,现有配置即授权使用该 provider/model,不再追加 CLI/API 确认,其他生成规则继续遵循系统 `imagegen` 技能。
6. 如果当前 MCP、工具或 API 不支持单次生成多张图片,而用户需要多张图片,应发起多次生成请求,不要把需求降级成只生成一张。使用内置脚本时,为每张图片指定不同的 `--out` 并分别执行。
7. 生成派生产物时(例如基于现有图片/原型做变体、扩图、局部重绘、风格迁移、素材补图或素材拆分),必须把原图或相关原型截图作为参考图传给图片生成工具;使用内置脚本时通过重复的 `--image` 传入本地文件路径,不要只在提示词里文字描述,也不要传远程 URL。如果当前只有页面或预览链接,先导出真实运行截图到本地,再把该本地路径传入。

如果没有可用的 Make 图片配置,则回退到系统 `imagegen` 的默认行为。

提示词应聚焦实际图片用途:目标画面、输出角色、尺寸/比例、视觉风格、精确文案、透明背景需求,以及输出保存位置。UI、网站、插画和普通视觉素材都按正式生产资产描述,不默认使用低保真表达。

写给第三方图片生成工具的提示词,应按真实产品或正式界面来描述,不要传递内部 `prototype` 概念。只有用户明确要求低保真、线框图、占位图或草稿时,才使用 `wireframe`、`placeholder`、`draft` 等词。

## 设备与画布比例

在调用图片生成工具前,必须先判断目标载体,并把画布比例写进提示词或工具参数。`gpt-image-2` 的 API 参数 `size` 可以使用符合约束的自定义尺寸:宽高都必须是 `16` 的倍数,最长边必须小于 `3840px`,长短边比例不超过 `3:1`,总像素在 `655360` 到 `8294400` 之间。设备真实比例写进提示词;不要把不符合约束的设备物理尺寸直接传给 `size`。

用户没有明确指定尺寸时,按以下默认值处理:

| 场景 | 默认画布 | 工具尺寸建议 |
| --- | --- | --- |
| 手机 App、小程序、移动端 H5 整屏 | 竖向手机屏,约 `9:19.5`,接近 `390x844` | `768x1664`;需要更高清时用 `1168x2528`,并在提示词中强调手机整屏比例 |
| PC Web、后台、SaaS、桌面端产品页 | 横向桌面屏,`16:10` 或接近 `1440x900` | `1440x896`;需要更高清时用 `1920x1200` |
| 平板界面 | `4:3` 或 `3:4`,按横竖屏需求选择 | 使用最接近的合规 `size`,例如 `1536x2048` 或 `2048x1536`,并在提示词中说明平板横/竖屏 |
| 图标、头像、独立素材矩阵 | `1:1` | `1024x1024` |
| 插画、头像、装饰图等独立素材 | `1:1`;按素材形态调整 | `1024x1024`,并在提示词中说明透明背景或素材边界 |
| Banner、封面、Hero 背景 | `16:9`、`21:9` 或用户指定平台比例 | 使用满足 Image 2 约束的横向尺寸,例如 `1920x1088` |

如果用户说“移动端、手机、App、小程序、H5”,默认使用竖向手机整屏;不要生成方图、横图、平板比例或宽得像桌面端的手机 UI。如果用户说“PC、Web、后台、SaaS、Dashboard、管理端、桌面端”,默认使用横向桌面画布;不要生成手机竖屏。只有用户明确说“自适应/多端”时,才分别生成移动端和 PC 端多张图。

写最终提示词时加入类似字段:

```text
Canvas/aspect ratio: mobile portrait phone screen, about 9:19.5, 390x844 logical pixels.
Device target: modern smartphone app full screen.
Frame treatment: show one complete phone screen UI, no browser chrome unless requested, no tablet or desktop layout.
Avoid: square canvas, landscape canvas, tablet-like proportions, cropped UI, extra outer mockup scene.
```
Files in this package (3)
  • SKILL.md 6 KB
  • agents/openai.yaml 1 KB
  • scripts/request-image.mjs 5 KB

Versions

The database has no other skills named ui-image-generation.

Identical content appears in 2 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 8b88ada4e50c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100genimage
    Generate, edit, or create any image — photos, illustrations, icons, thumbnails, hero images, banners, placeholder visuals, website graphics, social media assets, product shots, logos, diagrams, or any visual content. Use this skill whenever the task involves creating an image,…
  • 100image-generation
    Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
  • 100image
    Generates raster images (icons, illustrations, textures) via the logged-in Codex CLI image tool. Use when an agent needs a real image but has no native image generation.
  • 100cursor-image-generation
    Generate and iterate images in Cursor using the built-in image model and strong prompts. Use when creating icons, illustrations, UI mockups, diagrams, marketing visuals, or any raster asset from a text description or reference image.
  • 90minecraft-imagegen
    Generate or edit Minecraft raster assets such as pack icons, promo art, concept textures, thumbnails, banners, and UI mockups. Use when the deliverable is a bitmap image rather than JSON, SVG, or code-native assets.
  • 100codex-image
    Generates or edits raster images (illustrations, concept art, UI mockups, sprites, icons, textures, photos, cutouts) with OpenAI Codex's built-in image generation, using the ChatGPT login Codex is signed into. Saves PNGs where the project needs them, runs batches in parallel,…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.