菜单
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run Claude Code (preferred), Codex CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.
Reorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA.
Edit PDFs with natural-language instructions using the nano-pdf CLI.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
| name | nano_banana_pro |
| description | Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). |
| homepage | https://ai.google.dev/ |
| metadata | {"crocbot":{"emoji":"🍌","requires":{"bins":["uv"],"env":["GEMINI_API_KEY"]},"primaryEnv":"GEMINI_API_KEY","install":[{"id":"uv-brew","kind":"brew","formula":"uv","bins":["uv"],"label":"Install uv (brew)"}]}} |
Use the bundled script to generate or edit images.
Default Storage Path: All generated media MUST be saved to {workspaceDir}/assets/.
Generate
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "{workspaceDir}/assets/output.png" --resolution 1K
Edit (single image)
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "{workspaceDir}/assets/output.png" -i "/path/in.png" --resolution 2K
Multi-image composition (up to 14 images)
uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scene" --filename "output.png" -i img1.png -i img2.png -i img3.png
API key
GEMINI_API_KEY env varskills."nano-banana-pro".apiKey / skills."nano-banana-pro".env.GEMINI_API_KEY in ~/.crocbot/crocbot.jsonNotes
1K (default), 2K, 4K.yyyy-mm-dd-hh-mm-ss-name.png.MEDIA: line for crocbot to auto-attach on supported chat providers.