Skill

gemini-computer-use

From sundial-org-awesome-openclaw-skills-4

Builds and runs Gemini 2.5 Computer Use agents with Playwright for browser automation. Implements agent loops (screenshot → function_call → action → response) with safety confirmations for risky UI actions.

Python

Playwright

automation

ai-ml

Install

npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin sundial-org-awesome-openclaw-skills-4

Tool Access

This skill uses the workspace's default tool permissions.

Preview

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

Supporting Assets

references/google-computer-use.mdscripts/computer_use_agent.py

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.2k

mcp-builder

9 files

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

anthropics-skills-13

124.2k

canvas-design

20 files

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

anthropics-skills-13

124.2k

Stats

Stars586

Forks75

Last CommitFeb 1, 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