Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research.
安装
npx skills add inference-sh/skills --skill agent-browsernpx skills add inference-sh/skills --skill agent-browser -a claude-code -gnpx skills add inference-sh/skills --skill agent-browser -a codex -ggemini skills install https://github.com/inference-sh/skills.git --path tools/utilities/agent-browsergh skill install inference-sh/skills agent-browsergit clone --depth 1 https://github.com/inference-sh/skills /tmp/inference-sh__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/inference-sh__skills/tools/utilities/agent-browser ~/.claude/skills/agent-browser # Claude Code
cp -R /tmp/inference-sh__skills/tools/utilities/agent-browser ~/.agents/skills/agent-browser # Codex, Cursor, Gemini CLI, Copilot, OpenCode