godot-asset-generator
Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot. Covers the full art pipeline from concept art and style guides to final sprites, sprite sheets, and import configuration. This skill should be used when creating game art, generating sprites, making tilesets, creating UI elements, or preparing assets for Godot import. Keywords: game assets, AI art, DALL-E, Replicate, fal.ai, sprite sheet, tileset, Godot, pixel art, character sprite, game art, texture, animation frames.
What this skill does
# Godot Asset Generator
Generate game assets using AI image generation APIs and prepare them for use in Godot 4.x. This skill covers the complete art pipeline from concept to Godot-ready sprites.
## When to Use This Skill
Use this skill when:
- Generating game sprites, characters, or objects using AI
- Creating tilesets for platformers or top-down games
- Generating UI elements, icons, or menu assets
- Batch-generating animation frames
- Preparing AI-generated assets for Godot import
- Creating consistent asset sets with style guides
Do NOT use this skill when:
- Creating 3D models or textures (2D assets only)
- Manual pixel art or illustration (use art software)
- Complex frame-by-frame animation (use animation tools)
- Working with existing assets (use Godot directly)
## Prerequisites
**Required:**
- Deno runtime installed
- At least one API key:
- `OPENAI_API_KEY` for DALL-E 3
- `REPLICATE_API_TOKEN` for Replicate (SDXL, Flux)
- `FAL_KEY` for fal.ai
**Optional:**
- ImageMagick for advanced image processing
- Godot 4.x project for import file generation
## Quick Start
### Generate a Single Image
```bash
deno run --allow-env --allow-net --allow-write scripts/generate-image.ts \
--provider dalle \
--prompt "pixel art knight character, front view, 16-bit style, transparent background" \
--output ./assets/knight.png
```
### Batch Generate Animation Frames
```bash
deno run --allow-env --allow-net --allow-read --allow-write scripts/batch-generate.ts \
--spec ./batch-spec.json \
--output ./generated/
```
### Create Sprite Sheet
```bash
deno run --allow-read --allow-write scripts/pack-spritesheet.ts \
--input ./generated/*.png \
--output ./sprites/player-sheet.png \
--columns 4
```
## Core Workflow
### Phase 1: Style Definition
Define your art style before generating assets:
1. **Choose Art Style**: Pixel art, hand-drawn, painterly, or vector
2. **Create Style Guide**: Document colors, modifiers, and constraints
3. **Test Prompts**: Generate samples to validate style consistency
```json
{
"style": "pixel-art",
"resolution": 64,
"palette": "limited-16-colors",
"modifiers": "16-bit, no anti-aliasing, clean pixels"
}
```
### Phase 2: Asset Generation
Generate assets using the appropriate provider:
1. **Single Assets**: Use `generate-image.ts` for individual images
2. **Batch Assets**: Use `batch-generate.ts` for multiple related assets
3. **Iterate**: Refine prompts based on results
### Phase 3: Post-Processing
Prepare raw AI output for game use:
1. **Background Removal**: Extract sprites from backgrounds
2. **Color Correction**: Normalize palette if needed
3. **Resize**: Scale to exact game resolution
4. **Trim/Pad**: Remove whitespace, add sprite padding
```bash
deno run --allow-read --allow-write scripts/process-sprite.ts \
--input ./raw/knight.png \
--output ./processed/knight.png \
--remove-bg \
--resize 64x64 \
--filter nearest
```
### Phase 4: Godot Integration
Prepare assets for Godot import:
1. **Pack Sprite Sheets**: Combine frames into optimized sheets
2. **Generate Import Files**: Create `.import` with optimal settings
3. **Configure Animations**: Set up SpriteFrames resources
## API Provider Selection
| Provider | Best For | Quality | Cost | Speed |
|----------|----------|---------|------|-------|
| DALL-E 3 | Consistency, high detail | Excellent | $$$ | Medium |
| Replicate | Style control, variations | Very Good | $$ | Medium |
| fal.ai | Fast iteration, testing | Good | $ | Fast |
### DALL-E 3 (OpenAI)
Best for high-quality, consistent results. Excellent prompt following.
```bash
--provider dalle --model dall-e-3
```
- Sizes: 1024x1024, 1792x1024, 1024x1792
- Quality: standard, hd
- Style: vivid, natural
### Replicate (SDXL/Flux)
Best for style control and cheaper batch generation.
```bash
--provider replicate --model stability-ai/sdxl
```
- More model options (SDXL, Flux, specialized)
- Negative prompts supported
- ControlNet and img2img available
### fal.ai
Best for rapid iteration and testing prompts.
```bash
--provider fal --model fal-ai/flux/schnell
```
- Fastest inference
- Good for prototyping
- Lower cost per image
## Prompting by Art Style
### Pixel Art
```
"pixel art [subject], 16-bit style, clean pixels, no anti-aliasing,
limited color palette, retro game sprite, transparent background"
```
**Key modifiers**: `16-bit`, `8-bit`, `pixel art`, `retro`, `clean pixels`, `no anti-aliasing`
**Avoid**: `realistic`, `detailed`, `smooth`, `gradient`
### Hand-Drawn / Illustrated
```
"hand-drawn illustration of [subject], ink lines, watercolor texture,
sketch style, game art, white background"
```
**Key modifiers**: `hand-drawn`, `illustration`, `ink lines`, `sketch`, `watercolor`
### Painterly / Concept Art
```
"digital painting of [subject], concept art style, painterly brush strokes,
dramatic lighting, game asset"
```
**Key modifiers**: `digital painting`, `concept art`, `painterly`, `brush strokes`
### Vector / Flat Design
```
"flat design [subject], vector art style, clean edges, solid colors,
minimal shading, game icon, transparent background"
```
**Key modifiers**: `flat design`, `vector`, `clean edges`, `solid colors`, `minimal`
## Script Reference
### generate-image.ts
Generate a single image from any supported provider.
```bash
deno run --allow-env --allow-net --allow-write scripts/generate-image.ts [options]
Options:
--provider <name> Provider: dalle, replicate, fal (required)
--prompt <text> Generation prompt (required)
--output <path> Output file path (required)
--model <name> Specific model (optional, provider-dependent)
--size <WxH> Image size, e.g., 1024x1024 (default: 1024x1024)
--style <name> Style preset: pixel-art, hand-drawn, painterly, vector
--negative <text> Negative prompt (Replicate/fal only)
--quality <level> Quality: standard, hd (DALL-E only)
--json Output metadata as JSON
-h, --help Show help
```
### batch-generate.ts
Generate multiple images from a specification file.
```bash
deno run --allow-env --allow-net --allow-read --allow-write scripts/batch-generate.ts [options]
Options:
--spec <path> Path to batch specification JSON (required)
--output <dir> Output directory (required)
--concurrency <n> Parallel requests (default: 2)
--delay <ms> Delay between requests (default: 1000)
--resume Resume from last successful
--json Output results as JSON
-h, --help Show help
```
**Batch Spec Format:**
```json
{
"provider": "replicate",
"model": "stability-ai/sdxl",
"style": "pixel-art",
"basePrompt": "16-bit pixel art, game sprite, transparent background",
"assets": [
{ "name": "player-idle", "prompt": "knight standing idle, front view" },
{ "name": "player-walk-1", "prompt": "knight walking, frame 1 of 4" },
{ "name": "player-walk-2", "prompt": "knight walking, frame 2 of 4" }
]
}
```
### process-sprite.ts
Post-process generated images for game use.
```bash
deno run --allow-read --allow-write scripts/process-sprite.ts [options]
Options:
--input <path> Input image path (required)
--output <path> Output image path (required)
--remove-bg Remove background (make transparent)
--resize <WxH> Resize to dimensions
--filter <type> Resize filter: nearest, linear (default: nearest)
--trim Trim transparent whitespace
--padding <n> Add padding pixels
--color-key <hex> Color to make transparent (e.g., ff00ff)
-h, --help Show help
```
### pack-spritesheet.ts
Pack multiple sprites into a sprite sheet.
```bash
deno run --allow-read --allow-write scripts/pack-spritesheet.ts [options]
Options:
--input <pattern> Input files (glob pattern, required)
--output <path> Output sprite sheet path (required)
--columns <n> Number of columns (default: auto)
--padding <n> Padding bRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.