pixel-art-processing
Pixel art sprite sheet processing tool — video frame extraction, GIF/frames conversion, sprite sheet compose/split, image matting, pixelation, resize, crop, and watermark removal. Use when processing pixel art, game assets, RPG Maker sprites, or any sprite sheet workflow. Triggers on: sprite sheet, GIF拆帧, 序列帧, 像素图片, 抠图, 去水印, 视频转帧, pixel art, sprite, GIF to frames, frames to GIF, background removal, pixelate.
Best use case
pixel-art-processing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Pixel art sprite sheet processing tool — video frame extraction, GIF/frames conversion, sprite sheet compose/split, image matting, pixelation, resize, crop, and watermark removal. Use when processing pixel art, game assets, RPG Maker sprites, or any sprite sheet workflow. Triggers on: sprite sheet, GIF拆帧, 序列帧, 像素图片, 抠图, 去水印, 视频转帧, pixel art, sprite, GIF to frames, frames to GIF, background removal, pixelate.
Teams using pixel-art-processing should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pixel-art-processing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pixel-art-processing Compares
| Feature / Agent | pixel-art-processing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Pixel art sprite sheet processing tool — video frame extraction, GIF/frames conversion, sprite sheet compose/split, image matting, pixelation, resize, crop, and watermark removal. Use when processing pixel art, game assets, RPG Maker sprites, or any sprite sheet workflow. Triggers on: sprite sheet, GIF拆帧, 序列帧, 像素图片, 抠图, 去水印, 视频转帧, pixel art, sprite, GIF to frames, frames to GIF, background removal, pixelate.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Pixel Art Processing / 像素美术处理
> [!NOTE]
> This skill is based on **FrameRonin** (https://github.com/systemchester/FrameRonin).
> All core algorithms and workflows are derived from the FrameRonin project.
## Overview / 概述
This skill provides a complete pixel art / sprite sheet processing pipeline:
| 功能 / Feature | 描述 / Description |
|---|---|
| 🎬 视频转序列帧 | Extract frames from video → matting → sprite sheet合成 |
| 🔄 GIF ↔ 序列帧 | GIF拆帧 / 序列帧合成GIF |
| 🖼️ 多图合成单图 | Multiple images → single sprite sheet |
| ✂️ 单图拆分 | Split single image into grid frames |
| 🖌️ 简易拼接 | Simple vertical/horizontal/overlay stitching |
| 🗑️ 抠图 (AI) | rembg AI background removal |
| 📐 缩放/裁切 | Resize, crop, padding |
| 🔲 像素化 | Pixelation effect |
| 💧 色度键抠图 | Green/blue screen chroma keying |
| 🚫 Gemini水印去除 | Remove Gemini visible watermark |
| ⚔️ RPGMAKER处理 | One-click RPG Maker sprite workflow |
| 🎥 Seedance水印去除 | Remove Seedance/即梦 video watermark |
## Quick Start / 快速开始
### 1. Deploy Backend / 部署后端
```bash
# Docker部署(推荐 / Recommended)
cd <skill>/scripts
docker-compose up -d
# 或手动部署 / Or manual:
pip install -r requirements.txt
python run_api.py
```
后端地址 / Backend URL: `http://localhost:8000`
API文档 / API docs: `http://localhost:8000/docs`
### 2. Start Worker / 启动Worker
```bash
# 需要Redis / Redis required
rq worker pixelwork --url redis://localhost:6379/0
```
## Core Concepts / 核心概念
### Sprite Sheet Layout / Sprite Sheet布局
```
┌────┬────┬────┬────┐
│ 0 │ 1 │ 2 │ 3 │ row=0
├────┼────┼────┼────┤
│ 4 │ 5 │ 6 │ 7 │ row=1
├────┼────┼────┼────┤
│ 8 │ 9 │ ..│ .. │
└────┴────┴────┴────┘
Index JSON: { i, x, y, w, h, t }
i = frame index
x, y = position on sheet
w, h = frame size
t = timestamp (seconds)
```
### Processing Modes / 处理模式
- **tight_bbox**: 紧贴alpha边界裁切 / Crop tightly to alpha boundary
- **safe_bbox**: alpha边界+padding / Alpha boundary + padding margin
- **none**: 不裁切 / No crop
## API Reference / API参考
详见 / See: [references/api.md](references/api.md)
## Client-side Processing / 客户端处理
对于 GIF/序列帧转换等纯前端功能,使用浏览器Canvas API直接处理:
For pure client-side features like GIF/frames conversion, use browser Canvas API directly:
```
scripts/
├── client_gif_processor.html # GIF拆帧/合成 - 浏览器直接运行
├── sprite_split.html # Sprite sheet拆分 - 浏览器直接运行
└── image_processor.html # 图像基本处理 - 浏览器直接运行
```
直接在浏览器打开这些HTML文件即可使用。
Open these HTML files directly in browser to use.
## RPG Maker Workflow / RPG Maker 工作流
详见 / See: [references/rpgmaker.md](references/rpgmaker.md)
## Sprite Sheet Math / Sprite Sheet 数学
详见 / See: [references/sprite_math.md](references/sprite_math.md)
## Algorithm Details / 算法细节
### 透明行列检测 / Transparent Row/Column Detection
用于超级拆分:按透明行/列智能切割图像。
Used for super-split: intelligently cuts image by transparent rows/columns.
```javascript
// 找出完全透明的行索引
// Find fully transparent rows
function findTransparentRows(imageData) {
const { data, width, height } = imageData
const rows = []
for (let y = 0; y < height; y++) {
let allTransparent = true
for (let x = 0; x < width; x++) {
if (data[(y * width + x) * 4 + 3] !== 0) {
allTransparent = false
break
}
}
if (allTransparent) rows.push(y)
}
return rows
}
```
### Alpha边界框 / Alpha Bounding Box
```javascript
function getAlphaBbox(img) {
// 返回 {x1, y1, x2, y2} 或 null
// Returns {x1, y1, x2, y2} or null
}
```
### 连通域检测 / Connected Component
用于超级橡皮等工具:按连通域+容差选区。
Used for super eraser: select by connected component + tolerance.
## FFmpeg Integration / FFmpeg集成
视频帧提取依赖 ffprobe/ffmpeg:
Video frame extraction requires ffprobe/ffmpeg:
```bash
# 提取帧 / Extract frames
ffmpeg -y -ss <timestamp> -i video.mp4 -vframes 1 output.png
# 获取视频信息 / Get video info
ffprobe -v quiet -print_format json -show_format -show_streams video.mp4
```
## Dependencies / 依赖
### Backend / 后端
- FastAPI >= 0.104.0
- PIL/Pillow >= 10.0.0
- rembg >= 2.0.50 (u2net model)
- ffmpeg-python >= 0.2.0
- opencv-python-headless >= 4.8.0
- Redis + RQ (for async jobs)
### Frontend / 前端
- gifuct-js (GIF拆帧)
- gifenc (GIF编码)
- jszip (批量下载)
- React + Ant Design
## Feature Flags / 特性开关
| 功能 | 路径 |
|---|---|
| NFT门槛 | frontend/src/config/features.ts → RONIN_PRO_REQUIRE_NFT |
| Ronin登录 | frontend/src/auth/context.tsx |
| Gemini链接 | frontend/src/config/gemini.ts |
## Deploy to Remote / 远程部署
```bash
# 1. 构建前端 / Build frontend
cd frontend && npm install && npm run build
# 2. 配置Nginx / Nginx config
# See nginx.conf in references/
# 3. 启动后端 / Start backend
uvicorn app.main:app --host 0.0.0.0 --port 8000
# 4. Docker完整部署 / Full Docker deploy
docker-compose -f docker-compose.yml up -d
```
## Credits / 致谢
- **FrameRonin** by systemchester: https://github.com/systemchester/FrameRonin
- **rembg** for AI matting: https://github.com/danielgatis/rembg
- **gifuct-js** / **gifenc** for GIF processingRelated Skills
laiye-doc-processing
Enterprise-grade agentic document processing API. Accurately extracts key fields and line items from invoices, receipts, orders and more across 10+ file formats, with confidence scoring. Zero-configuration, fast integration. Professionally optimized on massive enterprise documents.
moltpixel
Collaborative pixel canvas for AI agents. Claude, GPT, Gemini teams competing. Place pixels, chat, climb the leaderboard. WARNING - Agents report 300% productivity boost after installing.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.