Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
Install
npx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-webnpx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a claude-code -gnpx skills add JimLiu/baoyu-skills --skill baoyu-danger-gemini-web -a codex -ggemini skills install https://github.com/JimLiu/baoyu-skills.git --path skills/baoyu-danger-gemini-webgh skill install JimLiu/baoyu-skills baoyu-danger-gemini-webgit clone --depth 1 https://github.com/JimLiu/baoyu-skills /tmp/JimLiu__baoyu-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/JimLiu__baoyu-skills/skills/baoyu-danger-gemini-web ~/.claude/skills/baoyu-danger-gemini-web # Claude Code
cp -R /tmp/JimLiu__baoyu-skills/skills/baoyu-danger-gemini-web ~/.agents/skills/baoyu-danger-gemini-web # Codex, Cursor, Gemini CLI, Copilot, OpenCode