Pixel Art Exporter
Export sprites to PNG, GIF, or spritesheet formats with JSON metadata for game engines. Use when the user wants to "export", "save", "output", "render", "generate", "create file", mentions file formats like "PNG", "GIF", "animated GIF", "spritesheet", "sprite sheet", "texture atlas", "tile sheet", or game engine integration with "Unity", "Godot", "Phaser", "Unreal", "GameMaker". Trigger on layout terms ("horizontal", "vertical", "grid", "packed", "strip"), scaling ("2x", "4x", "upscale", "pixel-perfect"), file operations ("save as", "export to", "output to"), metadata formats ("JSON", "XML", "metadata", "atlas data"), and delivery terms ("for web", "for game", "for Twitter", "for itch.io", "optimized").
What this skill does
# Pixel Art Exporter
## Overview
The Pixel Art Exporter Skill enables exporting pixel art sprites from Aseprite to various formats optimized for different use cases. This includes single images (PNG), animated GIFs, spritesheets, and JSON metadata for game engines.
**Core Capabilities:**
- Export single frames or entire animations as PNG images
- Generate animated GIFs with customizable timing and looping
- Create spritesheets in multiple layouts (horizontal, vertical, grid, packed)
- Generate JSON metadata for game engines (Unity, Godot, Phaser, generic)
- Scale exports with pixel-perfect upscaling (1x, 2x, 4x, etc.)
- Handle transparency, background colors, and frame-specific exports
**Export Formats Supported:**
- **PNG**: Single images or frame sequences with transparency
- **GIF**: Animated GIFs with frame timing and loop control
- **Spritesheet**: Texture atlases with various packing algorithms
- **JSON**: Frame metadata, animation tags, layer information
This Skill works with the pixel-mcp server tools to produce production-ready assets for web, games, and applications.
## When to Use
Invoke this Skill when the user:
- **Wants to export or save**: "export this sprite", "save as PNG", "generate a spritesheet"
- **Mentions file formats**: "PNG", "GIF", "spritesheet", "sprite sheet", "texture atlas", "JSON"
- **Prepares for game engines**: "export for Unity", "Godot spritesheet", "Phaser animation"
- **Needs specific outputs**: "export just frame 3", "create a tileset", "save each layer separately"
- **Requests scaling**: "export at 2x size", "scale up 4x", "upscale for retina displays"
- **Wants animation exports**: "make this into a GIF", "export the animation", "save all frames"
- **Needs metadata**: "include JSON data", "export with coordinates", "frame information"
**Example Triggers:**
- "Can you export this character sprite as a PNG?"
- "I need a spritesheet for my game engine"
- "Save this animation as an animated GIF"
- "Export at 4x scale for high-resolution displays"
- "Generate a texture atlas with JSON metadata"
- "Export just the 'run' animation tag"
## Instructions
### 1. Exporting Single Images (PNG)
**For static sprites or single frames:**
1. **Get Sprite Information First**
```
Use mcp__aseprite__get_sprite_info to understand:
- Current dimensions
- Number of frames
- Available layers
- Color mode and transparency settings
```
2. **Export PNG with Transparency**
```
Use mcp__aseprite__export_png:
- file_path: Absolute path (e.g., "/path/to/output/sprite.png")
- frame_number: Specific frame (0-indexed) or omit for current frame
- layer: Specific layer name or omit for merged output
- scale: Scaling factor (1, 2, 4, etc.) - default is 1
```
3. **Export Options**
- **Transparent background**: Default behavior, preserves alpha channel
- **Specific background**: Use layer visibility or flatten before export
- **Single frame from animation**: Specify frame_number parameter
- **Specific layer only**: Provide layer name to export just that layer
**Example Workflow:**
```
1. Get sprite info to verify dimensions and frame count
2. Export PNG: mcp__aseprite__export_png with desired frame and scale
3. Confirm file creation and report dimensions to user
```
### 2. Exporting Animated GIFs
**For animations intended for web or presentations:**
1. **Verify Animation Setup**
```
Use mcp__aseprite__get_sprite_info to check:
- Frame count (needs 2+ frames)
- Frame durations (timing information)
- Animation tags (if specific tag requested)
- Sprite dimensions
```
2. **Export GIF**
```
Use mcp__aseprite__export_gif:
- file_path: Output path (e.g., "/path/to/animation.gif")
- animation_tag: Optional - specific tag name to export
- loop: true (infinite loop) or false (play once)
- scale: Upscaling factor if needed
```
3. **GIF Optimization Considerations**
- GIF format has 256-color limit - ensure palette is optimized
- Frame timing is preserved from Aseprite frame durations
- Transparency is supported but may have edge artifacts
- File size increases with dimensions and frame count
**Example Workflow:**
```
1. Verify sprite has multiple frames
2. Export GIF with appropriate loop setting
3. Report file size and frame count to user
4. Suggest optimization if file is large (>1MB)
```
### 3. Creating Spritesheets
**For game engines and texture atlases:**
1. **Understand Layout Requirements**
**Layout Types:**
- **Horizontal**: All frames in a single row (good for scrolling animations)
- **Vertical**: All frames in a single column (good for CSS animations)
- **Grid**: Frames arranged in rows and columns (balanced dimensions)
- **Packed**: Optimized packing to minimize texture size (engine-specific)
2. **Export Spritesheet**
```
Use mcp__aseprite__export_spritesheet:
- file_path: Output PNG path (e.g., "/path/to/spritesheet.png")
- layout: "horizontal", "vertical", "grid", or "packed"
- animation_tag: Optional - export specific animation only
- scale: Upscaling factor
- padding: Pixels between frames (default 0, common: 1-2)
- include_json: true to generate metadata file
```
3. **JSON Metadata Structure**
When `include_json: true`, creates a .json file with:
```json
{
"frames": [
{
"filename": "frame_0.png",
"frame": {"x": 0, "y": 0, "w": 32, "h": 32},
"spriteSourceSize": {"x": 0, "y": 0, "w": 32, "h": 32},
"sourceSize": {"w": 32, "h": 32},
"duration": 100
}
],
"meta": {
"app": "Aseprite",
"version": "1.3.x",
"format": "RGBA8888",
"size": {"w": 256, "h": 32},
"scale": "1"
}
}
```
4. **Layout Selection Guidelines**
- **Horizontal**: Best for web/CSS sprite animations, simple scrolling
- **Vertical**: Mobile-friendly, vertical scrolling animations
- **Grid**: Unity, Godot - balanced texture dimensions (power-of-2)
- **Packed**: Advanced engines with atlas support (Phaser, LibGDX)
**Example Workflow:**
```
1. Ask user about target platform if not specified
2. Recommend layout based on use case
3. Export spritesheet with JSON metadata
4. Report texture dimensions and frame count
5. Provide integration code sample for their engine
```
### 4. Generating JSON Metadata
**For game engine integration:**
1. **Metadata Formats by Engine**
**Unity:**
- Use "grid" layout for Unity's Sprite Editor
- JSON provides frame coordinates for slicing
- Include padding to prevent texture bleeding
**Godot:**
- Use "horizontal" or "grid" layout
- JSON maps to AnimatedSprite frames
- Frame duration converts to FPS
**Phaser:**
- Use "packed" layout for optimal performance
- JSON follows Texture Packer format
- Supports trimmed sprites and rotation
**Generic/Custom:**
- Standard frame array with x, y, w, h coordinates
- Duration in milliseconds per frame
- Animation tag groupings
2. **Export with Metadata**
```
Always include JSON when exporting for game engines:
- Set include_json: true in export_spritesheet
- JSON file created with same name as PNG (different extension)
- Contains frame positions, durations, and sprite metadata
```
3. **Metadata Usage Examples**
**Parsing in JavaScript (Phaser):**
```javascript
this.load.atlas('sprite', 'spritesheet.png', 'spritesheet.json');
this.add.sprite(x, y, 'sprite', 'frame_0.png');
```
**Parsing in C# (Unity):**
```csharp
// Import spritesheet.png with Multiple sprite mode
// Use JSON to set sprite rectangles in Sprite Editor
```
### 5. Scaling Exports
**Pixel-perfect upscaling for high-resolution displays:**
1. **When to Scale**
- Retina/HiDPI displays: Use 2x or 4x
- Modern game engines: Export at native size, let engine scale
- Web: Export 2x and use CSS to scale down (sharper rendering)
- Print/markeRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.