Yuzhua OpenClaw Skill for Openclaw

A lightweight skill that enables local gesture-controlled AI conversations using palm movements and the OpenClaw gateway.

juguangyuan520-dotcom
v1.0.0
Mar 6, 2026
1
988
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install yuzhua

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install yuzhua using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Yuzhua OpenClaw Skill?

Yuzhua is a specialized project designed for local, hands-free AI interaction. By utilizing Openclaw Skills, users can deploy a system where an open palm triggers recording and a closed hand stops it to send a request. This skill handles the entire lifecycle of the Yuzhua gateway, ensuring that speech recognition, Voice Activity Detection (VAD), and Text-to-Speech (TTS) all run locally for maximum privacy and performance. It is architected to remain isolated from the core runtime, meaning it provides gesture capabilities without altering the main process behavior of your existing Openclaw Skills setup.

Yuzhua OpenClaw Skill Use Cases

  • Implementing hands-free AI controls in a workspace using Openclaw Skills.
  • Deploying local, private voice assistants that don't rely on cloud-based wake words.
  • Creating gesture-based interfaces for accessibility or sterile environment computing.
  • Rapidly testing local VAD and TTS workflows within the OpenClaw ecosystem.

How Yuzhua OpenClaw Skill Works

  1. The skill clones the Yuzhua repository and prepares the local environment within the OpenClaw workspace.
  2. It initializes a local server on port 8080 to handle the gesture-to-gateway communication.
  3. The system monitors video input for palm gestures: an open palm initiates the VAD-supported recording session.
  4. Closing the hand triggers the end of the recording and packages the audio for local transcription.
  5. The resulting text is routed through the OpenClaw gateway, and the AI response is played back via local TTS.

Yuzhua OpenClaw Skill Setup

To get started with this skill, run the following commands in the skill directory:

# Install dependencies and clone the repository
./scripts/install.sh

# Configure your environment
# Edit the .env file to add your specific tokens

# Start the Yuzhua gesture service
./scripts/start.sh

# Verify the connection to the gateway
./scripts/health_check.sh

Yuzhua OpenClaw Skill Data Schema & Taxonomy

The skill manages its state and configuration through specific environment variables and local files:

Item Description Default Value
YUZHUA_HOME Local directory for the Yuzhua application ~/.openclaw/workspace/apps/Yuzhua
YUZHUA_REPO_URL The source repository for the gesture engine https://github.com/juguangyuan520-dotcom/Yuzhua.git
.env Configuration file for API tokens and secrets Generated from .env.example
API Status Health check endpoint for transcriber and session http://127.0.0.1:8080/api/status

Yuzhua OpenClaw Skill Advanced Features

  • Runtime isolation: Runs as a separate process to ensure Openclaw Skills stability.
  • Automated Health Monitoring: Built-in scripts to check the status of the transcriber, gateway, and session token.
  • Local Processing: All VAD and gesture logic stays on-device for low-latency response times.
  • Process Management: Easy start/stop scripts that handle port management on the local machine.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*