A utility to compile AI-generated pixel character reference sheets and individual actions into validated, game-ready assets and engine scenes.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pixel-asset-compiler
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install pixel-asset-compiler using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Pixel Asset Compiler is a technical utility designed to transition AI-generated art into structured game engine files. By consuming character reference sheets alongside action-specific images, this tool produces deterministic, well-aligned sprite assets. It helps developers enforce consistency, eliminate background residues, and scale game assets while maintaining artistic intent.
As part of the Openclaw Skills collection, this system automates structural validation and export workflows. It bridges the gap between raw generative AI outputs and structured engine imports, providing tools to verify game-ready formats for platforms like Godot 4.
To install the compiler globally via npm, run the following command:
npm install --global pixel-asset-compiler
If you are developing locally within the repository, compile the CLI using:
npm run cli:build
You can then run the end-to-end workflow script:
node <skill-dir>/scripts/run-workflow.mjs --input <character-source> --output <generic-asset-dir> --target godot --target-output <godot-asset-dir>
The compiler expects a structured directory layout and produces validated outputs as shown below:
character-source/
├── reference.png
├── actions/
│ └── <action>.png
└── sprite-asset.manifest.json
The sprite-asset.manifest.json file contains semantic rules for each action:
| Property | Type | Description |
|---|---|---|
| fps | Integer | Frames per second for the animation |
| loop | Boolean | Defines if the animation should loop |
| frameCount | Integer | The exact count of frames within the action strip |
All quality gates and export reports are recorded to verify the compilation state.
Loading
Save Claude Notes captures Claude Code Q&A into Markdown notes with transcript-aware defaults and flexible save targets.

Converts TED talk PDFs or pasted English transcripts into structured bilingual notes, vocabulary lists, reading questions, and Obsidian Canvas maps.

Openclaw Skills that connect listeners and agents to the Excavationpro music portal, verify the vault and catalog, and route live discovery.

Openclaw Skills for Lovense LAN Control turns a zero-dependency Python CLI into safe, local-network control for Lovense toys and feedback scenes.

Batch-inserts "Made In China" into Amazon FBA label PDFs with barcode-aware positioning, test-page previews, and mixed-SKU support.

A unified shopping and deal aggregator designed to help users programmatically discover coupons, compare prices, and query welfares across multiple platforms.








































