pw-image-generation
🎯Skillfrom plugins-world/pw-skills
|Generates AI images through workflows supporting text-to-image, image-to-image, and batch image generation using multiple AI models.
Installation
npx skills add https://github.com/plugins-world/pw-skills --skill pw-image-generationSkill Details
Overview
# Claude Code Skills
个人 Claude Code 技能扩展。
技能列表
- pw-image-generation: AI 图像生成工作流（文生图、图生图、批量生成）
- pw-redbook-image: 小红书风格提示词模板
- pw-embedded-c-style: 嵌入式 C 代码风格助手（创建项目、优化代码）
查看各技能的 SKILL.md 了解详细使用方法。
安装
```bash
# 克隆仓库
git clone https://github.com/plugins-world/pw-skills ~/.claude/skills
# 安装 pw-image-generation 依赖
cd ~/.claude/skills/pw-image-generation && npm install
```
让 AI 帮你安装
你可以让 Claude 帮助你安装和配置技能：
```
请帮我安装 pw-image-generation skill：
- 进入 skill 目录并安装依赖
- 配置 ai-router 的 API Key：[你的 API Key]
- 创建测试项目并生成一张测试图片
```
获取 API Key：https://ai-router.plugins-world.cn/console/token
注意：
- API Key 是 ai-router 的密钥，支持多种模型
- 需要 GitHub 登录，请确保 GitHub 账号已开放邮箱展示
支持的模型
- gemini-3-pro-image-preview: Google Gemini 3 Pro 图像预览模型（生成）
- gemini-2.0-flash-exp: Google Gemini 2.0 Flash 实验模型（分析）
- 其他支持图像生成的模型
作者
牟勇 | https://ai-router.plugins-world.cn | 微信: 1254074921
More from this repository7
Generates creative image prompts tailored to the aesthetic and style of Xiaohongshu (Little Red Book), a popular Chinese social media platform.
Generates web-related content or performs web interactions using Google's Gemini AI model with potential experimental or high-risk features.
pw-embedded-c-style skill from plugins-world/pw-skills
Automatically generates and posts content to WeChat official accounts or personal WeChat Moments using AI-powered content creation and publishing workflows.
Generates professional, customizable cover images for documents, presentations, or social media using AI-powered image generation techniques.
I apologize, but I cannot confidently infer the specific purpose of the "pw-aippt-old" skill from the provided README. The README lists some skills like image generation and embedded C code style a...
Generates AI images through workflows supporting text-to-image, image-to-image, and batch image generation using multiple AI models like Google Gemini.