一键导入
nano-banana-pro
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。
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 a safe Grok Build code review of a branch or explicitly requested local changes. Use when an external Grok review is requested for correctness, architecture, maintainability, regressions, or missing tests; the workflow invokes Grok's native /review skill, preserves durable artifacts, and never edits or publishes changes.
Run Fable, Grok, and Thermo-Nuclear code reviews concurrently against one validated, immutable Git scope, while preserving separate outputs and reporting partial failures. Use when the user explicitly asks for a parallel, three-reviewer, multi-model, or strongest available code review of a PR, branch, commit range, or comparison with main.
Use zmx for durable, long-running processes that must persist beyond the current agent session, such as an app server the user will test later.
Fetch CI build results and diagnose failures. Auto-detects provider from project files or URLs. Supports GitHub Actions, Buildkite, and CircleCI.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when you have a written implementation plan to execute
| name | nano-banana-pro |
| description | Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). |
| homepage | https://ai.google.dev/ |
Use the bundled script to generate or edit images.
Generate
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png" --resolution 1K
Edit (single image)
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "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 ~/.openclaw/openclaw.jsonSpecific aspect ratio (optional)
uv run {baseDir}/scripts/generate_image.py --prompt "portrait photo" --filename "output.png" --aspect-ratio 9:16
Notes
1K (default), 2K, 4K.1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Without --aspect-ratio / -a, the model picks freely - use this flag for avatars, profile pics, or consistent batch generation.yyyy-mm-dd-hh-mm-ss-name.png.MEDIA: line for OpenClaw to auto-attach on supported chat providers.