← Back to Skills Marketplace
selena001

长图转小红书图片切割工具

by Selena001 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
145
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install changtu-xiaohongshu-cropper
Description
长图转小红书图片切割工具 - 将任意长图按小红书 3:4 比例自动切割,支持移动端协作。使用场景:用户需要将长图(如文档截图、设计稿等)切割成小红书友好的图片格式。
README (SKILL.md)

长图转小红书图片切割工具

🎯 使用场景

当用户需要将长图切割成小红书友好的图片时使用:

  1. 移动端场景:用户在手机 App 上,需要快速切割并发布
  2. 批量处理:多张图片需要统一尺寸和比例
  3. 自动化需求:需要自动填充空白、统一格式

📋 核心功能

  • ✅ 按小红书 3:4 比例切割(1080×1440px)
  • ✅ 自动去除底部多余内容(可配置高度)
  • ✅ 支持自定义起始位置
  • ✅ 自动填充最后一张图片的空白
  • ✅ 移动端协作流程(手机发图 → AI 切割 → 返回结果)

🚀 快速开始

方式 1:命令行工具(推荐)

# 基础用法(从顶部开始切割)
python cropper.py 长图.png

# 指定起始位置(如从 400px 开始)
python cropper.py 长图.png --start-y 400

# 完整参数
python cropper.py 长图.png \
  --start-y 0 \
  --logo-height 160 \
  --width 1080 \
  --height 1440 \
  --output ./output/

方式 2:GUI 工具(可视化)

# 启动 GUI
python cropper_gui.py

# 操作步骤:
# 1. 点击"选择图片"
# 2. 滚动查看长图
# 3. 点击选择起始位置(红线出现)
# 4. 点击"开始切割"
# 5. 自动打开输出目录

📱 移动端协作流程

当用户在手机 App 上时:

  1. 用户操作:

    • 打开长图
    • 发送原图或截图给 AI
    • 告知起始位置(如"从顶部开始"或"0px")
  2. AI 操作:

    • 接收图片
    • 使用切割工具处理
    • 按 3:4 比例切割
    • 逐张发送回用户
  3. 输出结果:

    • 小红书友好的 1080×1440px 图片
    • 已去除底部多余内容
    • 可直接发布

⚙️ 参数说明

参数 说明 默认值
input 输入图片路径(必需) -
--start-y 起始 Y 坐标 0
--logo-height 底部切除高度 160
--width 目标宽度 1080
--height 目标高度 1440
--format 输出格式(png/jpg) png
--output 输出目录 ./output/

🛠️ 技术规格

输入要求

  • 格式:PNG、JPG、JPEG、WEBP
  • 来源:任意长图(文档截图、设计稿等)

输出规格

  • 尺寸:1080×1440px(3:4 比例)
  • 格式:PNG(默认)或 JPG
  • 质量:95%

依赖安装

pip install Pillow

📁 文件结构

changtu-xiaohongshu-cropper/
├── SKILL.md              # 技能说明文档
├── scripts/
│   ├── cropper.py        # 命令行工具
│   └── cropper_gui.py    # GUI 工具
└── references/
    └── README.md         # 完整文档

💡 使用技巧

技巧 1:确定起始位置

  • 如果从最顶部开始:--start-y 0
  • 如果跳过标题栏:--start-y 300(根据实际调整)
  • 使用 GUI 工具可视化选择(推荐)

技巧 2:底部内容去除

  • 默认切除高度:160px
  • 如果去除不干净:增加数值(如 180)
  • 如果损失内容:减少数值(如 120)

技巧 3:批量处理

# PowerShell 批量处理
Get-ChildItem *.png | ForEach-Object {
    python cropper.py $_.Name --start-y 0 --logo-height 160
}

⚠️ 常见问题

Q1: 切割位置不准确?

A: 使用 GUI 工具,可以可视化选择起始位置

Q2: 底部内容去除不干净?

A: 调整 --logo-height 参数,增加或减少数值

Q3: 图片比例不对?

A: 确认参数是 --width 1080 --height 1440(3:4 比例)

Q4: 移动端如何使用?

A: 发送图片给 AI,告知起始位置,AI 代为切割

🔄 更新日志

v1.0.0(2026-03-20)

  • ✅ 初始版本发布
  • ✅ 命令行工具
  • ✅ GUI 工具
  • ✅ 移动端协作流程
  • ✅ 小红书 3:4 比例支持
  • ✅ 自动切除底部内容

📞 反馈与支持

  • 快速启动:python cropper_gui.py
  • 问题反馈:联系作者
Usage Guidance
This skill appears to be a straightforward local image cropper (CLI + GUI) and is coherent with its description. Before installing or running: 1) Inspect the included Python files (they are short and readable) and run them in an isolated environment (virtualenv) if you have any doubt. 2) Note the minor documentation inconsistencies (references to '飞书' and varying dimension examples); verify the width/height settings you want before batch-processing important images. 3) The publish guide references 'clawhub login' (a place where you would supply credentials) — do not provide account passwords or tokens to unknown services. 4) Install only required Python deps (Pillow; OpenCV is optional) and test on non-sensitive images to confirm behavior (logo removal may crop content). If you want additional assurance, run a static diff / open the scripts to verify there are no network calls or unexpected file-system accesses beyond the output directory.
Capability Analysis
Type: OpenClaw Skill Name: changtu-xiaohongshu-cropper Version: 1.0.0 The skill bundle provides a legitimate utility for splitting long images into aspect ratios suitable for social media (Xiaohongshu). Analysis of the Python scripts (cropper.py and cropper_gui.py) shows standard use of the Pillow library for image manipulation and Tkinter for the GUI, with no evidence of network communication, data exfiltration, or malicious command execution. The SKILL.md instructions are purely functional and do not contain any prompt injection or deceptive directives.
Capability Assessment
Purpose & Capability
The name/description (长图 -> 小红书 3:4 cropping) matches the included Python CLI and GUI scripts which implement cropping, logo removal, and fill behavior. Minor inconsistencies exist in comments/docs: some files mention '飞书' (Feishu) and 4:3 vs 3:4 wording and swapped default dimensions appear across README/SKILL.md (both 1080x1440 and 1440x1080 are referenced). These are documentation mismatches but do not indicate added capabilities or surprising requirements.
Instruction Scope
SKILL.md instructs running included Python scripts and installing Pillow (and optionally OpenCV) — the runtime instructions operate on local image files and the output directory. The instructions do not ask the agent to read unrelated files, environment variables, or to send data to external endpoints.
Install Mechanism
No automated install spec is included; this is instruction-and-code distribution. Dependencies are simple (pip install Pillow, optional opencv-python). There are no downloads from untrusted URLs or archive extraction steps in the skill metadata.
Credentials
The skill requires no environment variables, credentials, or config paths. The code only reads input images and writes outputs to a local output directory; optional OpenCV is local. No secrets access is requested.
Persistence & Privilege
Skill flags use defaults (not always:true). It does not request persistent system-wide privileges, nor does it modify other skills or agent configuration based on the provided files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install changtu-xiaohongshu-cropper
  3. After installation, invoke the skill by name or use /changtu-xiaohongshu-cropper
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
changtu-xiaohongshu-cropper v1.0.0 - Initial release. - Provides command-line and GUI tools to crop long images into Xiaohongshu-friendly 3:4 (1080×1440px) format. - Features automatic bottom cropping with customizable height and start position. - Supports mobile collaboration workflow for quick image processing. - Includes batch processing and automatic blank-filling for the last image piece.
Metadata
Slug changtu-xiaohongshu-cropper
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 长图转小红书图片切割工具?

长图转小红书图片切割工具 - 将任意长图按小红书 3:4 比例自动切割,支持移动端协作。使用场景:用户需要将长图(如文档截图、设计稿等)切割成小红书友好的图片格式。 It is an AI Agent Skill for Claude Code / OpenClaw, with 145 downloads so far.

How do I install 长图转小红书图片切割工具?

Run "/install changtu-xiaohongshu-cropper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 长图转小红书图片切割工具 free?

Yes, 长图转小红书图片切割工具 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 长图转小红书图片切割工具 support?

长图转小红书图片切割工具 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 长图转小红书图片切割工具?

It is built and maintained by Selena001 (@selena001); the current version is v1.0.0.

💬 Comments