Use when the user asks to generate OR edit an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」「幫我去背」「把這張圖的背景去掉」). The skill drafts a Chinese + English prompt pair and waits for explicit approval. After approval it uses the host-native executor: Codex calls its built-in image_gen tool directly, while Claude Code keeps the Codex CLI background workflow.
安装
npx skills add KerberosClaw/kc_ai_skills --skill gpt-image-gennpx skills add KerberosClaw/kc_ai_skills --skill gpt-image-gen -a claude-code -gnpx skills add KerberosClaw/kc_ai_skills --skill gpt-image-gen -a codex -ggemini skills install https://github.com/KerberosClaw/kc_ai_skills.git --path gpt-image-gengh skill install KerberosClaw/kc_ai_skills gpt-image-gengit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills /tmp/KerberosClaw__kc_ai_skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/KerberosClaw__kc_ai_skills/gpt-image-gen ~/.claude/skills/gpt-image-gen # Claude Code
cp -R /tmp/KerberosClaw__kc_ai_skills/gpt-image-gen ~/.agents/skills/gpt-image-gen # Codex, Cursor, Gemini CLI, Copilot, OpenCode