Use when an agent needs to drive a real Chrome window via opencli â inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters â see opencli-adapter-author for that.
Install
npx skills add jackwener/OpenCLI --skill opencli-browsernpx skills add jackwener/OpenCLI --skill opencli-browser -a claude-code -gnpx skills add jackwener/OpenCLI --skill opencli-browser -a codex -ggemini skills install https://github.com/jackwener/OpenCLI.git --path skills/opencli-browsergh skill install jackwener/OpenCLI opencli-browsergit clone --depth 1 https://github.com/jackwener/OpenCLI /tmp/jackwener__OpenCLI
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/jackwener__OpenCLI/skills/opencli-browser ~/.claude/skills/opencli-browser # Claude Code
cp -R /tmp/jackwener__OpenCLI/skills/opencli-browser ~/.agents/skills/opencli-browser # Codex, Cursor, Gemini CLI, Copilot, OpenCode