ai-image-generator SKILL.md skillA

ai-image-generator from wwwzhouhui/skills_collection is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wwwzhouhui/skills_collection/ai-image-generator@git:20260726.4787fcc

Pins git:20260726.4787fcc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wwwzhouhui/skills_collection
Path
ai-teaching-media/ai-image-generator/SKILL.md
Versions recorded
1
Latest version
git:20260726.4787fcc, committed Jul 26, 2026
Size
9,420 bytes
Repository stars
284
License
none declared

通用图像生成执行层,支持 MuleRun Nano Banana 2、APImart GPT Image 2、Atlas Cloud GPT Image 2 和 Agnes Image 2.1 Flash 四种生图 API。通过 --provider 切换。支持 generation(纯文本生图)和 edit(带参考图修图)两种模式,单张和批量执行。这是被其他 skill 调用的基础设施 skill,不直接面向终端用户。当其他 skill(如 ai-image-generator、tech-article-diagram)需要调 API 生图时,调用本 skill 的 scripts/generate.py。不要用于:提示词撰写、风格注入、业务校验——这些由调用方 skill 负责。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 通用图像生成器

支持四种生图 API 的执行层,通过 `--provider` 参数切换。调用方 skill 负责 prompt 撰写、样式注入、业务校验;本 skill 只管"接收 prompt → 调 API → 返回结果"。

## 什么时候触发这个 skill

本 skill 是被其他 skill 调用的基础设施,不直接由用户触发。当 Claude 正在执行某个生图相关的 skill(如 `ai-image-generator`、`tech-article-diagram`)时,通过 bash 调用本 skill 的脚本。

## 生图 API 切换

通过 `--provider` 参数或环境变量自动检测选择生图平台:

```bash
# 方式 1: 自动检测 —— 只设一个环境变量就行
export APIMART_API_KEY=sk-xxx
python scripts/generate.py \
  --mode generation --prompt "..." --output-dir ./out
# 自动检测到 APIMART_API_KEY,使用 apimart

# 方式 2: 显式指定 —— 两个都设了时用这个覆盖
python scripts/generate.py \
  --provider apimart --mode generation --prompt "..." --output-dir ./out
```

| Provider | `--provider` | 环境变量 | 模型 |
|---|---|---|---|
| MuleRun | `mulerun` | `MULERUN_API_KEY` | Nano Banana 2 |
| APImart | `apimart` | `APIMART_API_KEY` | GPT Image 2 |
| Atlas Cloud | `atlascloud` | `ATLASCLOUD_API_KEY` | GPT Image 2 |
| Agnes | `agnes` | `AGNES_API_KEY` | Agnes Image 2.1 Flash(`agnes-image-2.1-flash`) |

**自动检测逻辑**(不传 `--provider` 时):
1. 仅发现一个 API Key → 自动使用对应 provider
2. 多个 API Key 同时存在 → **直接报错,要求显式指定 `--provider`**
3. 没有 API Key → 报错并提示设置

## 两种模式

### generation — 纯文本生图

从纯文字 prompt 生成图片,不依赖参考图。适合:概念图、流程图、信息图等。

```bash
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wwwzhouhui/skills_collection/ai-image-generator@sha256:2062eae0b234a337

The line at the top of this page pins the label git:20260726.4787fcc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gljbr7qzcfakg2lb.svg)](https://markdownregistry.com/a/art_gljbr7qzcfakg2lb)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 26, 2026.

versioncommittedcommitsizeaudit
git:20260726.4787fcc latest2026-07-26 4787fcc 9,420 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9420 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wwwzhouhui/skills_collection · 284 stars · license none declared · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gljbr7qzcfakg2lb
GET https://markdownregistry.com/api/v1/resolve?ref=wwwzhouhui/skills_collection/ai-image-generator
GET https://markdownregistry.com/api/v1/blob/2062eae0b234a337858571fdf58d36c07bfe4fed39b3f7745b75cc9d16e2d2a2

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wwwzhouhui/skills_collection

ai-teaching-media SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/SKILL.md · AI 教学媒体一体化技能包。在一个 skill 内串联 6 个子能力:通用生图执行层、技术长文智能插图、学科知识点竖版信息图、教学动图+配音教学视频、短视频 3:4…
git:20260726.4787fcc · audit A · 284 stars
article-explainer-video SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/article-explainer-video/SKILL.md · 把一篇技术长文/论文解读自动做成章节式解说视频(1080p, 5-8 分钟)。双主题:warm(奶油底+珊瑚红+cozy-handdrawn 透明插图,亲和感)和 midnight(深蓝黑底+琥珀金+宋体标题+executive-tech…
git:20260726.4787fcc · audit A · 284 stars
edu-subject-infographic SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/edu-subject-infographic/SKILL.md · 将任意学科知识点转化为竖版教育信息图(9:16)。用户只需要输入一个知识点名称(如"声现象"、"勾股定理"、"光合作用"),Skill 自动完成:识别学科/年级/章节、拆解3-5个核心子概念、分配主题色系、为每个子概念生成具体插图描述、构建…
git:20260726.4787fcc · audit A · 284 stars
edu-teaching-animation SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/edu-teaching-animation/SKILL.md · 把单个学科概念(中文/英文都行,如"声现象""杠杆原理""光合作用")自动做成动态教学内容。两种产出都由 HyperFrames 渲染、共用同一个 index.html(mode 变量切换):① 配音教学视频 — 分镜 + Minimax…
git:20260726.4787fcc · audit A · 284 stars
short-video-cover SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/short-video-cover/SKILL.md · 根据视频口播文案,为视频号/抖音/小红书短视频生成 3:4 竖版封面图。当用户需要给短视频做封面、配缩略图、出竖版题图时使用。触发词包括:做视频封面、生成视频封面图、视频号封面、抖音封面、小红书视频封面、竖版封面、3:4…
git:20260726.4787fcc · audit A · 284 stars
tech-article-diagram SKILL.md skill
wwwzhouhui/skills_collection · ai-teaching-media/tech-article-diagram/SKILL.md · 为技术长文自动识别插图位置,并生成 16:9 概念图/流程图/对比图/架构图。支持七种风格:手绘网格笔记本风(notebook)、专业扁平信息图(infographic)、现代高级科技商务风(executive-tech)、温暖手绘卡片风(…
git:20260726.4787fcc · audit A · 284 stars
dify-dsl-generator SKILL.md skill
wwwzhouhui/skills_collection · dify-dsl-generator/SKILL.md · 专业的 Dify 工作流 DSL/YML 文件生成器,根据用户业务需求自动生成完整的 Dify 工作流配置文件,支持各种节点类型和复杂工作流逻辑
v1.0.0 · audit A · 284 stars
excel-report-generator SKILL.md skill
wwwzhouhui/skills_collection · excel-report-generator/SKILL.md · Automatically generate Excel reports from data sources including CSV, databases, or Python data structures. Supports…
git:20251112.c625f19 · audit A · 284 stars
github-readme-generator SKILL.md skill
wwwzhouhui/skills_collection · github-readme-generator/SKILL.md · Generate professional GitHub project README.md with standard structure including project intro, features, installation…
v1.0.0 · audit A · 284 stars
github-trending-wan-skill SKILL.md skill
wwwzhouhui/skills_collection · github-trending-wan-skill/SKILL.md · 抓取 GitHub Trending 当前前 5 个开源项目,先把摘要字段翻译成中文,再生成低信息密度中文简报和 Wan 2.7 海报 prompt。支持 10 种视觉风格选择。Use when user asks for GitHub…
git:20260408.54dfe3d · audit A · 284 stars
github-trending SKILL.md skill
wwwzhouhui/skills_collection · github-trending/SKILL.md · 获取 GitHub Trending 前五项目的 README 与摘要,并发送企业微信消息。适用于热门项目跟踪、技术趋势简报与团队分享。
git:20260122.2bb4461 · audit A · 284 stars
grok-imagine-image SKILL.md skill
wwwzhouhui/skills_collection · grok-imagine-image/SKILL.md · 使用 grok-imagine-image 模型,通过兼容 Grok2API / OpenAI 风格的接口(`/v1/images/generations`)生成图片。当用户要求用 Grok Imagine /…
git:20260726.4787fcc · audit B · 284 stars

Every file in wwwzhouhui/skills_collection

Browse by kind, by grade A, or by owner.