Skills wavelet-world-model

Generates a world model representation from state inputs using discrete wavelet transforms (DWT) to capture multi-resolution temporal and spatial features.

install

source · Clone the upstream repo

git clone https://github.com/openclaw/skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/aadipapp/wavelet-worldmodel-skill" ~/.claude/skills/clawdbot-skills-wavelet-world-model && rm -rf "$T"

manifest: skills/aadipapp/wavelet-worldmodel-skill/SKILL.md

source content

Wavelet World Model Skill

This skill allows your OpenClaw agent to transform high-dimensional sequential state data into a compact world model representation using Wavelet Transforms.

It leverages multi-resolution analysis to efficiently encode BOTH high-frequency details (rapid changes) and low-frequency components (long-term dependencies), making it highly effective for robotic control, continuous state tracking, and predicting complex environments.

Commands

```
wavelet-model
```
: standardized command to initialize the wavelet world model and process state inputs.