重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
image-generation by guinacio/claude-image-gen
npx skills add https://github.com/guinacio/claude-image-gen --skill image-generation通过捆绑的 CLI 脚本使用 Google Gemini 生成专业的 AI 图像。
在以下情况立即调用:
Web 开发
placeholder.jpg、stock-photo.png)<section class="hero">)演示文稿和文档
应用程序
通过 bash 运行捆绑的 CLI 脚本:
node "${CLAUDE_PLUGIN_ROOT}/mcp-server/build/cli.bundle.js" \
--prompt "您的详细图像描述" \
--output "./path/to/output.png" \
--aspect-ratio "16:9"
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 标志 | 必需 | 默认值 | 描述 |
|---|---|---|---|
| --prompt, -p | 是 | - | 详细的图像描述 |
| --output, -o | 否 | 自动生成 | 输出文件路径 |
| --aspect-ratio, -a | 否 | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2 |
| --model, -m | 否 | gemini-3-pro-image-preview | 要使用的模型 |
| --output-dir, -d | 否 | 当前目录 | 输出目录 |
CLI 输出 JSON:
{"success": true, "filePath": "/path/to/generated-image.png"}
或出错时:
{"success": false, "error": "错误信息"}
使用以下公式构建有效的提示词:
[风格] [主题] [构图] [背景/氛围]
科技初创公司英雄图像
Minimalist 3D illustration of abstract geometric shapes floating in space,
soft gradient background from deep purple to electric blue, subtle glow effects,
modern professional aesthetic, wide composition for website header
电子商务产品
Clean product photography of modern wireless headphones on white marble surface,
soft studio lighting from left, subtle shadows, high-end minimalist aesthetic,
centered composition
博客文章标题
Aerial photography of winding river through autumn forest, golden hour lighting,
warm color palette with oranges and reds, cinematic wide shot, serene atmosphere
应用程序插图
Flat vector illustration of person organizing digital files on floating screens,
soft pastel colors, isometric perspective, clean lines, friendly approachable style
当您看到以下情况时,自动调用此技能:
<!-- 占位符检测 -->
<img src="placeholder.jpg" alt="Hero">
<!-- 操作:调用技能并生成自定义英雄图像 -->
<!-- 空的视觉区域 -->
<section class="features">
<h2>Our Features</h2>
<!-- No images -->
</section>
<!-- 操作:调用技能以创建功能插图 -->
/* 通用库存引用 */
.banner { background: url('stock-image.jpg'); }
/* 操作:调用技能以创建独特的背景 */
skill: "image-generation"可用模型是从 Gemini API 动态获取的。默认情况下,当 GEMINI_DEFAULT_MODEL 可用时,CLI 会使用它,否则会回退到第一个发现的具有图像生成能力的模型。
应该:
不应该:
关于高级提示词技巧:references/prompt-crafting.md
如果配置了 MCP 服务器,您也可以使用:
mcp__media-pipeline__create_asset
参数:prompt、outputPath、aspectRatio、model
每周安装次数
53
仓库
GitHub 星标数
26
首次出现
2026年2月9日
安全审计
安装于
opencode49
gemini-cli48
github-copilot48
codex48
amp48
kimi-cli48
Generate professional AI images using Google Gemini via the bundled CLI script.
Invoke immediately when:
Web Development
placeholder.jpg, stock-photo.png)<section class="hero"> without images)Presentations & Documents
Applications
Run the bundled CLI script via bash:
node "${CLAUDE_PLUGIN_ROOT}/mcp-server/build/cli.bundle.js" \
--prompt "Your detailed image description" \
--output "./path/to/output.png" \
--aspect-ratio "16:9"
| Flag | Required | Default | Description |
|---|---|---|---|
| --prompt, -p | Yes | - | Detailed image description |
| --output, -o | No | auto-generated | Output file path |
| --aspect-ratio, -a | No | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 2:3, 3:2 |
| --model, -m | No | gemini-3-pro-image-preview | Model to use |
| --output-dir, -d | No | current directory | Output directory |
The CLI outputs JSON:
{"success": true, "filePath": "/path/to/generated-image.png"}
Or on error:
{"success": false, "error": "Error message"}
Use this formula for effective prompts:
[Style] [Subject] [Composition] [Context/Atmosphere]
Hero Image for Tech Startup
Minimalist 3D illustration of abstract geometric shapes floating in space,
soft gradient background from deep purple to electric blue, subtle glow effects,
modern professional aesthetic, wide composition for website header
E-commerce Product
Clean product photography of modern wireless headphones on white marble surface,
soft studio lighting from left, subtle shadows, high-end minimalist aesthetic,
centered composition
Blog Post Header
Aerial photography of winding river through autumn forest, golden hour lighting,
warm color palette with oranges and reds, cinematic wide shot, serene atmosphere
App Illustration
Flat vector illustration of person organizing digital files on floating screens,
soft pastel colors, isometric perspective, clean lines, friendly approachable style
Automatically invoke this skill when you see:
<!-- Placeholder detection -->
<img src="placeholder.jpg" alt="Hero">
<!-- Action: Invoke skill and generate a custom hero image -->
<!-- Empty visual section -->
<section class="features">
<h2>Our Features</h2>
<!-- No images -->
</section>
<!-- Action: Invoke skill to create feature illustrations -->
/* Generic stock reference */
.banner { background: url('stock-image.jpg'); }
/* Action: Invoke skill to create a unique background */
skill: "image-generation" immediatelyAvailable models are fetched dynamically from the Gemini API. By default, the CLI uses GEMINI_DEFAULT_MODEL when it is available, otherwise it falls back to the first discovered image-capable model.
DO:
DON'T:
For advanced prompt techniques: references/prompt-crafting.md
If the MCP server is configured, you can also use:
mcp__media-pipeline__create_asset
Parameters: prompt, outputPath, aspectRatio, model
Weekly Installs
53
Repository
GitHub Stars
26
First Seen
Feb 9, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode49
gemini-cli48
github-copilot48
codex48
amp48
kimi-cli48
AI界面设计评审工具 - 全面评估UI/UX设计质量、检测AI生成痕迹与优化用户体验
58,500 周安装
市场推广计划制定工具:3步生成可执行GTM策略,助力产品上市与客户获取
212 周安装
Excalidraw图表生成器 - AI驱动,自然语言描述一键生成流程图、架构图、思维导图
220 周安装
Terraform/OpenTofu专家:高级IaC自动化、状态管理与多云部署实践指南
214 周安装
docs-seeker:AI驱动的技术文档智能发现与分析工具,支持llms.txt优先搜索与仓库分析
213 周安装
Symfony API Platform状态提供器:设计API合约、序列化与安全的最佳实践
214 周安装
数据库管理员技能指南:云原生数据库管理、自动化运维与高可用性最佳实践
215 周安装