Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Install
npx skills add SawyerHood/dev-browser --skill dev-browsernpx skills add SawyerHood/dev-browser --skill dev-browser -a claude-code -gnpx skills add SawyerHood/dev-browser --skill dev-browser -a codex -ggemini skills install https://github.com/SawyerHood/dev-browser.git --path skills/dev-browsergh skill install SawyerHood/dev-browser dev-browsergit clone --depth 1 https://github.com/SawyerHood/dev-browser /tmp/SawyerHood__dev-browser
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/SawyerHood__dev-browser/skills/dev-browser ~/.claude/skills/dev-browser # Claude Code
cp -R /tmp/SawyerHood__dev-browser/skills/dev-browser ~/.agents/skills/dev-browser # Codex, Cursor, Gemini CLI, Copilot, OpenCode