💡 Summary
An AI-powered content creation assistant that clarifies user needs, conducts research, and adapts content for multiple platforms.
🎯 Target Audience
🤖 AI Roast: “The skill relies on external search engines, which may expose it to data leakage risks. To mitigate, ensure that sensitive data is not processed or logged during usage.”
Risk: Medium. Review: shell/CLI command execution; outbound network access (SSRF, data egress); API keys/tokens handling and storage; dependency pinning and supply-chain risk. Run with least privilege and audit before enabling in production.
oh-my-writing-skill
功能特性
- 🔍 深度研究:使用 ddgs + DuckDuckGo 获取背景资料,无需 API Key
- 🖼️ 智能配图:使用 ddgs + DuckDuckGo 搜索和下载相关图片,无需 API Key
- ✍️ 内容创作:生成高质量的 AI 创作内容
- 🤖 AI人性化:优化 AI 生成痕迹,使内容更自然
- 📱 多平台适配:一键转换为知乎、小红书、微信公众号文章风格
项目结构
.claude/
└── skills/
├── content-creator/ # 主协调器(Skill,用户手动调用)
├── deep-research/ # 网络搜索(后台 Skill)
├── image-search/ # 图片搜索(后台 Skill)
├── image-processing/ # 图片处理(后台 Skill)
├── general-writing/ # 通用写作(后台 Skill)
├── humanizer-cn/ # 中文人性化(后台 Skill)
├── zhihu-converter/ # 知乎转换(后台 Skill)
├── xiaohongshu-converter/ # 小红书转换(后台 Skill)
└── wechat-converter/ # 微信公众号转换(后台 Skill)
安装
- 克隆项目并进入目录
cd writing-skill
- 创建、激活虚拟环境并安装依赖
python -m venv .venv .venv\Scripts\activate # Windows source .venv/bin/activate # Linux/Mac pip install -r requirements.txt
使用方法
在 Claude Code 中加载此工作区,然后使用 /content-creator 命令:
/content-creator 「酱油」一词为什么正在被「生抽」和「老抽」替代?发知乎和小红书。
说明:
content-creator是主入口 Skill,需要手动调用(disable-model-invocation: true)- 8 个子 Skills(deep-research、image-search 等)是后台能力,不会出现在菜单(
user-invocable: false) - Claude 会在 content-creator 内部自动协调这些子 Skills
工作流程
graph LR User[用户需求] --> Confirm[需求确认] subgraph Research [资料准备] direction LR Confirm --> CheckResearch{需研究?} CheckResearch -->|是| DeepResearch[深度研究<br/>deep-research] CheckResearch -->|否| Write DeepResearch --> Write end subgraph Creation [内容生成] direction LR Write[内容创作<br/>general-writing] --> CheckImg{需配图?} CheckImg -->|是| SearchImg[图片搜索<br/>image-search] CheckImg -->|否| Humanize SearchImg --> ProcessImg[图片处理<br/>image-processing] ProcessImg --> Humanize[人性化优化<br/>humanizer-cn] end subgraph Platform [多平台适配] direction TB Humanize --> Target{目标平台} Target -->|知乎| Zhihu[知乎格式<br/>zhihu-converter] Target -->|小红书| RED[小红书格式<br/>xiaohongshu-converter] Target -->|微信| WeChat[微信格式<br/>wechat-converter] end Zhihu --> Output[最终输出] RED --> Output WeChat --> Output style User fill:#e1f5ff style Output fill:#e8f5e9 style DeepResearch fill:#fff3e0 style SearchImg fill:#fff3e0 style ProcessImg fill:#fff3e0 style Write fill:#fff3e0 style Humanize fill:#f3e5f5 style Zhihu fill:#fce4ec style RED fill:#fce4ec style WeChat fill:#fce4ec
示例展示
每个示例包含完整的输出文件:
research*.md- 研究资料draft.md- 初始草稿humanized.md- 人性化优化版本zhihu.md/xiaohongshu.md/wechat.md- 平台适配版本images/- 配图资源
致谢
License
MIT
Pros
- Supports multiple platforms
- No API key required for research and image search
- Generates high-quality content
- Optimizes AI-generated text for a natural feel
Cons
- Requires manual invocation of the main skill
- Dependency on external search engines
- Limited to specific platforms
- Potential for content quality variability
Related Skills
novel-writer-skills
A“This tool is like a writing coach that never sleeps—just don't expect it to write your novel for you!”
screen-creative-skills
A“Powerful, but the setup might scare off the impatient.”
payload
A“Payload's architecture may expose risks such as dependency vulnerabilities and potential CSRF attacks. Regular updates and using secure coding practices can mitigate these risks.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author z0gSh1u.
