Skill

gemini-computer-use

Builds and runs Gemini 2.5 Computer Use agents with Playwright to automate browser tasks via screenshot-function-action loops and safety confirmations for risky actions.

Playwright

Python

ai-ml

automation

Install

npx claudepluginhub joshuarweaver/cascade-code-general-misc-4 --plugin am-will-codex-skills-5

Tool Access

This skill uses the workspace's default tool permissions.

Preview

1. Source the env file and set your API key:

Supporting Assets

env.examplereferences/google-computer-use.mdscripts/computer_use_agent.py

SKILL.md

Similar Skills

using-git-worktrees

Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.

superpowers

168.3k

subagent-driven-development

3 files

Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.

superpowers

168.3k

dispatching-parallel-agents

Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.

superpowers

168.3k

Stats

Stars889

Forks46

Last CommitJan 17, 2026

Actions

View Source View Plugin View on GitHub View README

Tags

Gemini Computer Use

Quick start

Source the env file and set your API key:

cp env.example env.sh
$EDITOR env.sh
source env.sh

Create a virtual environment and install dependencies:

python -m venv .venv
source .venv/bin/activate
pip install google-genai playwright
playwright install chromium

Run the agent script with a prompt:

python scripts/computer_use_agent.py \
  --prompt "Find the latest blog post title on example.com" \
  --start-url "https://example.com" \
  --turn-limit 6

Browser selection

Default: Playwright's bundled Chromium (no env vars required).

Choose a channel (Chrome/Edge) with COMPUTER_USE_BROWSER_CHANNEL.

Use a custom Chromium-based executable (e.g., Brave) with COMPUTER_USE_BROWSER_EXECUTABLE.

If both are set, COMPUTER_USE_BROWSER_EXECUTABLE takes precedence.

Core workflow (agent loop)

Capture a screenshot and send the user goal + screenshot to the model.

Parse function_call actions in the response.

Execute each action in Playwright.

If a safety_decision is require_confirmation, prompt the user before executing.

Send function_response objects containing the latest URL + screenshot.

Repeat until the model returns only text (no actions) or you hit the turn limit.

Operational guidance

Run in a sandboxed browser profile or container.

Use --exclude to block risky actions you do not want the model to take.

Keep the viewport at 1440x900 unless you have a reason to change it.

Resources

Script: scripts/computer_use_agent.py

Reference notes: references/google-computer-use.md

Env template: env.example