What it does
OpenClaw 中文教程(4500+ Star · 已出版纸质书):安装、配置、Skills、飞书接入与避坑|作者的 GPT-6 / Codex / Claude Code 新项目见 README 顶部
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for NEXTAI_API_KEY (per the README)
- Category Coding
For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/xianyu110-awesome-openclaw-tutorial)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one awesome-openclaw-tutorial | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Maker | xianyu110 | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| GitHub stars | 4,582 | 465,460 | 233,910 | 149,364 | 144,149 |
| Last code change | Oct 4, 2026 | Nov 17, 2026 | Apr 20, 2026 | Nov 17, 2026 | Nov 17, 2026 |
| License | – | MIT | – | Apache-2.0 | MIT |
1 skills (instruction sets) by xianyu110 that an AI reads and follows · not an MCP server
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodex
From the maker’s README and the folders in the repo
Install
Is it safe?
- Who made it
GitHub account xianyu110 (person), 7 years old
- Use and upkeep
★ 4,582 stars · code last changed Oct 4, 2026
- Any scripts?
5 scripts that can run on a computer: prepare-upload.sh, release/bananapro-image-gen/scripts/generate_image.py, scripts/generate_image.py, test.sh and 1 more
- Uses the internet?
Scripts that go online: release/bananapro-image-gen/scripts/generate_image.py, scripts/generate_image.py
- Changes machine-wide settings?
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 2ae37f8 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Option 1Upload to claude.ai (web and app)
Download from GitHub
This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier
Download from GitHub (whole repo) ↗
Unzip it, then zip only the .claude/.skills/bananapro-image-gen folder again. The ZIP must have a banana-pro-image-generation folder with SKILL.md at the top level, no loose files
Open Skills on claude.ai and upload
+Create skillUpload a skillpick banana-pro-image-generation.zip
No Upload button? Turn on file creation first
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com
Option 1Let Claude Code install it
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /bananapro-image-gen or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.claude/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/xianyu110/awesome-openclaw-tutorial.git /tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8/.claude/.skills/bananapro-image-gen' ~/.claude/skills/bananapro-image-genRestart Claude Code, then type /bananapro-image-gen or ask for a matching task and Claude picks it up
ChatGPT desktop app
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Option 1Let ChatGPT install it
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Put the folder there yourself
Put the banana-pro-image-generation folder at ~/.agents/skills/banana-pro-image-generation
~ is your home folder ($HOME)
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/xianyu110/awesome-openclaw-tutorial.git /tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8/.claude/.skills/bananapro-image-gen' ~/.agents/skills/bananapro-image-gen
After installing
- ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
- To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
- Codex picks up newly installed skills by itself; if one does not show up, restart Codex
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
ChatGPT on the web and mobile
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Option 1Let Codex install it
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.agents/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/xianyu110/awesome-openclaw-tutorial.git /tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8/.claude/.skills/bananapro-image-gen' ~/.agents/skills/bananapro-image-genRestart Codex, then ask for a matching task; Codex lists the skill
Option 1Let Cursor install it
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick bananapro-image-gen
Checked against official docs Nov 12, 2026 · Source: cursor.com
For Terminal users
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Open Terminal
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
Copy the skill folder to ~/.cursor/skills
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
git clone --depth 1 https://github.com/xianyu110/awesome-openclaw-tutorial.git /tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-xianyu110-awesome-openclaw-tutorial-2ae37f8/.claude/.skills/bananapro-image-gen' ~/.cursor/skills/bananapro-image-genIn Cursor’s Agent chat, type / and pick bananapro-image-gen
Option 1Let the AI install it
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
✓ Commands checked Nov 17, 2026
View the original SKILL.md
The text below comes from the maker’s repo, not from PopNx MCP
5,508 characters · Open the full file on GitHub
---
name: "Banana Pro Image Generation"
description: "使用 Gemini 3 Pro Image 生成图片,支持白板图、Logo设计、社交媒体配图等多种场景"
version: "1.0.0"
author: "xianyu110"
compatibility: ["claude-code", "cursor", "github-copilot", "openclaw"]
tags: ["image-generation", "ai-art", "gemini", "whiteboard", "creative"]
---
# Banana Pro Image Generation Skill
当用户需要生成图片、设计Logo、创建白板图或制作社交媒体配图时,使用此技能。
## 核心能力
你可以帮助用户:
1. **文生图**:根据文字描述生成各种风格的图片
2. **白板图**:生成手写风格的概念图、流程图、对比表格
3. **Logo设计**:创建简约现代的Logo和图标
4. **社交媒体配图**:生成适合各平台的配图
5. **概念可视化**:将抽象概念转化为直观的图像
## 使用场景
### 场景1:用户需要教程配图
**用户说**:"帮我生成一张白板图,展示OpenClaw的核心架构"
**你应该**:
1. 理解用户需求(白板图、手写风格、架构图)
2. 构建详细的提示词
3. 调用生成脚本
4. 返回生成的图片
**示例提示词**:
```
生成一张白板图片,手写字体风格,内容是OpenClaw核心架构:
标题:OpenClaw 核心架构
三大组件:
📦 Gateway 网关
• 会话管理
• 消息路由
• 多平台连接
🤖 AI 智能体
• 理解指令
• 执行任务
• 返回结果
🔧 Skills 系统
• 扩展功能
• 无限可能
工作流程(用箭头连接):
用户消息 → Gateway → AI智能体 → Skills → 返回结果
用手写字体,添加框图、箭头、图标等手绘元素
```
### 场景2:用户需要Logo设计
**用户说**:"帮我设计一个AI助手的Logo"
**你应该**:
1. 询问具体需求(颜色、风格、用途)
2. 构建专业的Logo设计提示词
3. 生成多个方案供选择
**示例提示词**:
```
设计一个AI助手Logo,要求:
- 形状:圆形或方形
- 颜色:蓝色渐变
- 元素:抽象的大脑或机器人图案
- 风格:现代简约,科技感
- 用途:适合用在社交媒体头像和网站
```
### 场景3:用户需要对比图表
**用户说**:"生成一张对比图,展示OpenClaw vs ChatGPT"
**你应该**:
1. 整理对比维度
2. 构建清晰的表格式提示词
3. 生成易读的对比图
**示例提示词**:
```
生成一张对比表格图片,清晰易读,内容是:
标题:OpenClaw vs ChatGPT
对比维度:
1. 部署方式
OpenClaw: 本地/云端 ✓
ChatGPT: 在线服务
2. 文件访问
OpenClaw: 支持 ✓
ChatGPT: 不支持 ✗
3. 功能扩展
OpenClaw: Skills系统 ✓
ChatGPT: 固定功能 ✗
4. 成本
OpenClaw: 按需付费 ✓
ChatGPT: 订阅制
使用表格形式,清晰对比
```
## 调用方法
### 基础调用
```bash
python scripts/generate_image.py \
--prompt "你构建的详细提示词" \
--filename "output.png"
```
### 高清图片(2K/4K)
```bash
python scripts/generate_image.py \
--prompt "你的提示词" \
--filename "output.png" \
--resolution 2K
```
### 使用环境变量配置API
```bash
export NEXTAI_API_KEY="用户的API密钥"
python scripts/generate_image.py --prompt "你的提示词"
```
## 提示词构建技巧
### 技巧1:白板图提示词模板
```
生成一张白板图片,手写字体风格,内容包含:
- 标题:[主题]
- 核心要点:
1. [要点1]
2. [要点2]
3. [要点3]
- 使用箭头、框图、列表等手绘元素
```
### 技巧2:Logo设计提示词模板
```
设计一个[主题]Logo,要求:
- 形状:[圆形/方形/抽象]
- 颜色:[主色调]
- 元素:[核心元素]
- 风格:[现代/复古/简约]
- 用途:[社交媒体/网站/名片]
```
### 技巧3:对比图提示词模板
```
生成一张对比图,展示[A vs B]:
- 对比维度1:[A的特点] vs [B的特点]
- 对比维度2:[A的特点] vs [B的特点]
- 对比维度3:[A的特点] vs [B的特点]
使用表格或左右对比的形式,清晰易读
```
### 技巧4:概念图提示词模板
```
生成一张概念图,展示[主题]:
- 中心概念:[核心]
- 相关概念:[概念1、概念2、概念3]
- 概念之间的关系用箭头连接
使用思维导图或网络图形式
```
## 工作流程
当用户请求生成图片时,你应该:
1. **理解需求**
- 图片类型(白板图/Logo/配图/对比图)
- 风格要求(手写/现代/简约)
- 用途场景(教程/社交媒体/演示)
2. **构建提示词**
- 使用详细的描述
- 指定风格和元素
- 添加构图建议
3. **调用生成**
- 选择合适的分辨率
- 设置输出文件名
- 执行生成命令
4. **返回结果**
- 显示生成的图片
- 说明图片特点
- 提供修改建议
## 注意事项
1. **提示词要详细**:越详细的描述,生成效果越好
2. **指定风格**:明确说明需要的风格(手写/现代/简约等)
3. **合理分辨率**:
- 日常使用:1K(默认)
- 高清展示:2K
- 打印输出:4K
4. **成本控制**:
- 1K: ~$0.04/张
- 2K: ~$0.08/张
- 4K: ~$0.16/张
## 实战示例
### 示例1:教程配图
**用户**:"帮我生成第1章的总结图"
**你的回复**:
```
好的,我来为第1章生成一张总结白板图。
[调用生成脚本]
python scripts/generate_image.py \
--prompt "生成一张白板图片,手写字体风格,内容是OpenClaw第1章核心要点总结:
标题:OpenClaw 是什么?
核心定义:
• AI智能体Gateway网关
• 完全本地部署
• 数据隐私有保障
4大核心优势:
1️⃣ 本地部署 - 保护隐私
2️⃣ 文件访问 - 智能搜索
3️⃣ Skills扩展 - 无限可能
4️⃣ 多平台支持 - 随时随地
用手写字体,添加箭头、框图、下划线等手绘元素" \
--filename "chapter1_summary.png"
✅ 已生成第1章总结图:chapter1_summary.png
```
### 示例2:Logo设计
**用户**:"设计一个超级个体的Logo"
**你的回复**:
```
好的,我来为"超级个体"设计一个Logo。
[调用生成脚本]
python scripts/generate_image.py \
--prompt "设计一个'超级个体'Logo,要求:
- 形状:圆形,简洁大方
- 颜色:蓝色和橙色渐变
- 元素:一个人的剪影 + AI元素(如电路板纹理)
- 风格:现代科技感,简约
- 寓意:一个人 + AI = 无限可能
- 用途:适合用在社交媒体头像、网站Logo" \
--filename "super_individual_logo.png" \
--resolution 2K
✅ 已生成Logo设计:super_individual_logo.png
```
### 示例3:社交媒体配图
**用户**:"生成一张小红书配图,主题是AI效率提升"
**你的回复**:
```
好的,我来生成一张小红书配图。
[调用生成脚本]
python scripts/generate_image.py \
--prompt "生成一张小红书配图,主题是'AI效率提升10倍',要求:
- 尺寸:9:16竖版
- 配色:温暖的橙色和蓝色
- 文字:一个人 + AI = 效率提升10倍
- 元素:简约的人物剪影 + 上升的箭头
- 风格:现代简约,有科技感但不冰冷
- 适合小红书的视觉风格" \
--filename "xiaohongshu_ai_efficiency.png" \
--resolution 2K
✅ 已生成小红书配图:xiaohongshu_ai_efficiency.png
```
## 环境配置
### 方式1:使用环境变量(推荐)
```bash
export NEXTAI_API_KEY="your-api-key-here"
```
### 方式2:命令行参数
```bash
python scripts/generate_image.py \
--prompt "你的提示词" \
--api-key "your-api-key-here"
```
### 方式3:配置文件
在 `~/.openclaw/openclaw.json` 中配置:
```json
{
"skills": {
"bananapro-image-gen": {
"apiKey": "your-api-key-here",
"baseUrl": "https://tryallapi.com",
"model": "gemini-3-pro-image-preview"
}
}
}
```
## 参数说明
| 参数 | 说明 | 默认值 | 示例 |
|------|------|--------|------|
| `--prompt` | 图片描述(必需) | - | "画一只猫" |
| `--filename` | 输出文件名 | 自动生成 | "cat.png" |
| `--resolution` | 分辨率 | 1K | 1K/2K/4K |
| `--api-key` | API密钥 | 环境变量 | "sk-xxx" |
| `--model` | 模型名称 | gemini-3-pro-image-preview | - |
## 常见问题
### Q: 如何提高生成质量?
A: 使用详细的提示词,明确指定:
- 风格(手写/现代/简约)
- 颜色(蓝色/渐变/对比色)
- 元素(箭头/框图/图标)
- 构图(居中/左右对比/上下布局)
### Q: 生成失败怎么办?
A: 检查:
1. API Key是否正确
2. 网络连接是否正常
3. 提示词是否符合内容政策
### Q: 支持中文提示词吗?
A: 完全支持!Gemini对中文理解很好。
### Q: 如何控制成本?
A:
- 日常使用1K分辨率(最便宜)
- 只在需要高清时使用2K/4K
- 优化提示词,减少重复生成
## 文件结构
```
bananapro-image-gen/
├── SKILL.md # 本文档(必需)
├── README.md # 快速开始
├── scripts/
│ └── generate_image.py # 生成脚本
├── requirements.txt # Python依赖
└── .gitignore # Git忽略文件
```
## 更新日志
### v1.0.0 (2026-02-11)
- ✅ 初始版本
- ✅ 支持 Gemini 3 Pro Image
- ✅ 支持白板图、Logo、配图等多种场景
- ✅ 支持中文提示词
- ✅ 多种分辨率选择
## 许可证
MIT License
## 作者
- GitHub: [@xianyu110](https://github.com/xianyu110)
- 教程: [OpenClaw 超级个体实战指南](https://github.com/xianyu110/awesome-openclaw-tutorial)
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 4,582
- Maker
- xianyu110
- License
- No license stated This repo states no license. By default the author keeps all rights: ask before you share it or use it commercially.
- Last code change
- Oct 4, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 2
- Topics
- agent-skills, ai-agent, ai-assistant, ai-tools, automation, awesome, awesome-list, chinese, chinese-tutorial, claude-code, codex, feishu