跳到主要内容

nano-banana-2 精选

个人 agent skills 合集,涵盖多种日常与工程场景。原文:Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API. This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K.

仓库级简介:该 skill 尚无单独撰写的中文摘要
在 GitHub 打开

安装方式

cp -r skills/nano-banana-2 ~/.claude/skills/nano-banana-2

把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同,Claude Code 默认是 ~/.claude/skills/

整仓一次性获取:git clone --depth 1 https://github.com/intellectronica/agent-skills.git

依赖与权限

  • 需要 API Key —— 使用前需配置相应的密钥环境变量
  • 需要联网访问外部服务
  • 依赖外部命令:uv
  • 以上为按正文与 frontmatter 自动推断的信号,仅供参考;安装前建议先阅读原文。

SKILL.md 正文

来源 intellectronica/agent-skills@9b0e00a · 许可 CC0-1.0 · 内容未修改

Nano Banana 2 Image Generation & Editing

Generate new images or edit existing images with Nano Banana 2 (gemini-3.1-flash-image-preview).

Usage

Run the script using absolute or workspace-relative path (do NOT cd into the skill directory first):

Generate new image:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 512px|1K|2K|4K] [--aspect-ratio RATIO] [--api-key KEY]

Edit image(s) with references:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input1.png" [--input-image "path/to/input2.png" ...] [--resolution 512px|1K|2K|4K] [--aspect-ratio RATIO] [--api-key KEY]

Always run from the user's current working directory so outputs are saved in the active project context.

Model

Use model code:

  • gemini-3.1-flash-image-preview (Nano Banana 2)

Do not use gemini-3-pro-image-preview in this skill.

Resolution Options

Nano Banana 2 supports:

  • 512px (fastest, low-latency iteration)
  • 1K (default)
  • 2K
  • 4K

Map common user language:

  • "quick draft", "thumbnail", "tiny", "512", "0.5K" → 512px
  • no resolution mention → 1K
  • "2K", "medium", "normal" → 2K
  • "4K", "high-res", "ultra", "print quality" → 4K

Use uppercase K for 1K, 2K, 4K.

Aspect Ratios

Supported aspect ratios:

  • 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9

Map common requests:

  • square post / icon → 1:1
  • phone wallpaper / vertical reel → 9:16
  • widescreen / slide / hero image → 16:9
  • cinematic wide → 21:9
  • portrait print → 2:3 or 3:4
  • panorama banner → 4:1 or 8:1

If unspecified, let the model default behavior apply.

Reference Images (New in Gemini 3 Image workflows)

Provide up to 14 reference images when needed by repeating --input-image:

  • preserve character consistency
  • preserve object fidelity
  • combine multiple visual references into one output

Use one image for simple edits; use multiple images for composition or consistency-sensitive tasks.

API Key

Resolve API key in this order:

  1. --api-key argument
  2. GEMINI_API_KEY environment variable

If no key is available, stop and report a clear error.

Filename Generation

Generate filenames as: yyyy-mm-dd-hh-mm-ss-name.png

Examples:

  • 2026-02-26-17-31-04-japanese-garden.png
  • 2026-02-26-17-31-59-social-banner.png

Prompt Handling

For generation, pass the user's request as-is unless critically underspecified.

For editing, include explicit transformation instructions in the prompt and preserve the original intent.

Output

  • Save PNG to the current directory (or to a provided path in --filename)
  • Return the full saved path(s)
  • Do not read the output image back unless explicitly requested

Examples

Create a 4K widescreen image:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "Futuristic city skyline at blue hour with neon reflections" --filename "2026-02-26-17-45-00-futuristic-skyline.png" --resolution 4K --aspect-ratio 16:9

Edit with multiple references:

uv run ./.agents/skills/nano-banana-2/scripts/generate_image.py --prompt "Create a polished campaign image that keeps the exact logo details and character identity" --filename "2026-02-26-17-50-10-campaign-image.png" --input-image "logo.png" --input-image "character.png" --resolution 2K --aspect-ratio 4:5

质量与来源

所属仓库
intellectronica/agent-skills
仓库星标
295
最近更新
6 个月前
采集时间
今天
commit
9b0e00ad1b94
内容指纹
sha256:219cb690e66b15e
文件路径
skills/nano-banana-2/SKILL.md

相似 Skill

更多「办公」
opencli-adapter-author
Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level orientation to opencli, see opencli-usage.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-browser
Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing adapters — see opencli-adapter-author for that.
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what `opencli` can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
smart-search
基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时,尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时,务必使用此 skill
精选 jackwener/OpenCLI 3.0 万 原文
Gemini CLI
deeptutor-cli
终身个性化辅导系统:根据学习者情况持续调整教学方式。
精选 HKUDS/DeepTutor 4.1 万 仓库简介
Codex CLIMCP 客户端