gemini-computer-use — Claude Code skill: what it does, how to install
Runs Gemini 2.5 Computer Use agents with Playwright to drive browser workflows. It captures screenshots, calls UI actions, and prompts for confirmation on risky steps.
npx skills add am-will/codex-skills --skill gemini-computer-use -a claude-codeWhat gemini-computer-use does
The skill sets up an agent loop using the Gemini 2.5 Computer Use model. The script scripts/computer_use_agent.py takes a page screenshot, inspects model actions from function_call, and executes them via Playwright. Each step returns a new screenshot and location until the task finishes or hits --turn-limit.
You need Python, google-genai, and playwright with Chromium installed. Playwright's bundled Chromium runs by default. Setting COMPUTER_USE_BROWSER_CHANNEL switches to Chrome or Edge, while COMPUTER_USE_BROWSER_EXECUTABLE targets a custom binary and takes precedence.
Running these workflows in a sandbox profile or container prevents unintended account modifications. The --exclude flag stops forbidden UI operations, and the agent pauses whenever safety_decision flags an action as require_confirmation.
What it helps with
- automate browser workflows using visual actions from Gemini 2.5
- execute an inspect-action loop with screenshots and Playwright
- prevent risky browser commands using the
--excludeparameter - pause for manual user approval on sensitive UI interactions
Example prompts for the agent
- Set up a Gemini 2.5 browser agent using Playwright to extract test data.
- Run
scripts/computer_use_agent.pywith--turn-limit 6and human approval checks. - Configure
COMPUTER_USE_BROWSER_CHANNELto launch Chrome instead of bundled Chromium.
How to install gemini-computer-use
1Skills CLI (Vercel)
npx skills add am-will/codex-skills --skill gemini-computer-use -a claude-code2Manually: put the files in place
~/.claude/skills/gemini-computer-use/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gemini-computer-use/
1Skills CLI (Vercel)
npx skills add am-will/codex-skills --skill gemini-computer-use -a codex2Manually: put the files in place
.agents/skills/gemini-computer-use/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add am-will/codex-skills --skill gemini-computer-use -a cursor2Manually: put the files in place
.cursor/skills/gemini-computer-use/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install am-will/codex-skills gemini-computer-use2Manually: put the files in place
.github/skills/gemini-computer-use/SKILL.md1Skills CLI (Vercel)
npx skills add am-will/codex-skills --skill gemini-computer-use -a gemini-cli2Platform CLI
gemini skills install https://github.com/am-will/codex-skills --path skills/gemini-computer-useManually: put the files in place
.devin/skills/gemini-computer-use/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add am-will/codex-skills --skill gemini-computer-use -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gemini-computer-use
How to install gemini-computer-use in Claude Code?
Run npx skills add am-will/codex-skills --skill gemini-computer-use -a claude-code in your terminal.
What does gemini-computer-use do?
It provides an automation loop where Gemini 2.5 inspects screenshots and guides Playwright to click, scroll, and enter input.
Which browser does the agent run?
It uses Playwright's bundled Chromium by default, but you can select Chrome or a custom Chromium binary through environment variables.
