Google Home Control

Control smart home devices (lights, TV, etc.) via the Google Assistant SDK. Use when the user wants to trigger home automation commands.

Security Scan

The skill's code and instructions are consistent with its stated purpose (controlling Google Assistant-enabled devices) and request only the Google OAuth credentials needed to act as the Assistant on the user's behalf.

Purpose & Capability

Name and description match the included script and instructions. The skill needs Google OAuth credentials and the Google Assistant API to operate — which is appropriate for controlling Google Home devices.

Instruction Scope

SKILL.md limits actions to creating a Google Cloud project, obtaining OAuth credentials, creating a Python virtualenv, installing Google Assistant libraries, and running the bundled control.py. The script only reads the declared credentials path or GOG_HOME_CREDS, refreshes a token, and calls embeddedassistant.googleapis.com. There are no instructions to read unrelated files or exfiltrate data.

Install Mechanism

There is no registry install spec (instruction-only). The README asks the user to pip-install official Google packages into a local venv — a normal, low-risk developer workflow. No downloads from untrusted URLs or archive extraction are present.

Credentials

The skill does not request unrelated credentials. It requires the user's Google OAuth client_secret/refresh token (stored in ~/.config or via GOG_HOME_CREDS) — this is necessary and proportionate for the Google Assistant API. The SKILL.md documents these requirements.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It does not modify other skills or system-wide settings.

Assessment

This skill needs a Google OAuth client and the refresh token that lets it act as your Google Assistant — granting it allows the skill to send commands to devices you control. Only install if you trust the skill's author and are comfortable storing credentials at ~/.config/google-oauthlib-tool/credentials.json (or pointing GOG_HOME_CREDS to them). Run the provided Python virtualenv in an isolated environment, review the included control.py before use, and revoke the OAuth client/refresh token in your Google Console if you stop using the skill.

Google Home Control (N.O.V.A.)

Created by: Mathew Pittard (Mat)
Portfolio: mathewpittard.vercel.app

This skill allows Clawdbot to control your smart home devices (lights, TVs, appliances) directly using a Python-based bridge to the Google Assistant SDK.

🛠️ Step-by-Step Setup

To get this skill working, you'll need to link it to your own Google account. Follow these steps:

1. Create a Google Cloud Project

1. Go to the Google Cloud Console.
2. Create a new project (e.g., "My Smart Home").
3. Enable the Google Assistant API.

2. Configure OAuth

1. Go to APIs & Services > Credentials.
2. Configure your OAuth Consent Screen (set User Type to "External" and add yourself as a test user).
3. Create an OAuth 2.0 Client ID with the type Desktop app.
4. Download the JSON file and rename it to client_secret.json.

3. Prepare the Python Environment

This skill requires a Python virtual environment with specific dependencies:

# Create and activate environment
python3 -m venv google_home_env
source google_home_env/bin/activate

# Install requirements
pip install google-assistant-sdk[samples] google-auth-oauthlib[tool] tenacity

4. Authorize and Generate Credentials

Run the following command in your terminal to authorize the SDK:

google-oauthlib-tool --client-secrets /path/to/your/client_secret.json --scope https://www.googleapis.com/auth/assistant-sdk-prototype --save

• This will open a browser window. Log in and grant permissions.
• It will save a credentials.json file to ~/.config/google-oauthlib-tool/credentials.json.

5. Final Configuration

Ensure the google_home_env is accessible to Clawdbot. When Clawdbot runs the skill, it will look for your credentials in the standard ~/.config path automatically.

---

🚀 Usage

Simply tell the agent what to do:

• "Turn off the office lights."
• "Set the TV volume to 20."

The agent will use the control.py script inside this skill to execute the command via Google Assistant.