← 返回 Skills 市场
171
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install nanobananapro-openrouter
功能描述
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima...
安全使用建议
This skill appears to be what it says: it uploads images you explicitly provide (or generates images) to OpenRouter using the provided API key. Before installing, check/consider: 1) Provide only an OpenRouter API key (use a dedicated or limited key if possible). 2) Don’t pass sensitive images you wouldn’t want uploaded — any file you point at --input-image will be read and sent as a base64 data URL to openrouter.ai. 3) Ensure the 'uv' CLI and Python packages (requests, pillow) are available in your environment; the registry metadata omits these requirements. 4) If you want extra caution, run the scripts locally in a controlled environment first (with non-sensitive images) to confirm behavior. If you need me to, I can point out exactly where the key is read and where the upload happens in the code.
功能分析
Type: OpenClaw Skill
Name: nanobananapro-openrouter
Version: 1.0.3
The skill bundle is a legitimate tool for generating and editing images using the OpenRouter API (Google Gemini 3 Pro Image). The scripts (generate_image.py and generate_and_return.py) implement standard API interaction, image processing with PIL, and safe subprocess handling. No evidence of data exfiltration, malicious execution, or prompt injection attacks was found.
能力标签
能力评估
Purpose & Capability
The name/description (Nano Banana Pro via OpenRouter) aligns with the scripts: they call OpenRouter's API and use the Gemini image model. Minor mismatch: SKILL.md expects the 'uv' CLI and an OPENROUTER_KEY, but the skill registry metadata lists no required binaries or env vars.
Instruction Scope
Runtime instructions and scripts only read the input image(s) you explicitly provide, convert that image to a data URL, and POST to https://openrouter.ai. The scripts do not attempt to read arbitrary system files or unrelated environment variables.
Install Mechanism
This is instruction + script only (no install spec). The scripts list dependencies (requests, pillow) in comments but do not install them; SKILL.md and scripts assume the 'uv' runner and Python deps are present. That is a usability/integration omission, not malicious, but you must ensure those binaries/packages are installed securely.
Credentials
The only secret the code uses is an OpenRouter API key (OPENROUTER_KEY or --api-key), which is proportional to the task. However, registry metadata did not declare this required env var; the SKILL.md and scripts do require it — verify and provide only an appropriate API key.
Persistence & Privilege
The skill is not always-enabled, does not request elevated privileges, and does not attempt to modify other skills or system-wide configs.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install nanobananapro-openrouter - 安装完成后，直接呼叫该 Skill 的名称或使用
/nanobananapro-openrouter触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.3
- Updated usage instructions to use the generic `/path/to/this/skill/` instead of a specific user directory.
- Default output directory changed to `./output_images/` relative to the skill root, not a home directory.
- Examples, usage, and workflow steps now reference the generic skill path instead of hardcoded user-specific paths.
- No code changes; documentation and directory references clarified for easier adoption.
v1.0.2
- Removed the _meta.json file from the skill package.
- No user-facing changes to features, commands, or behavior.
- Version bump for minor internal/packaging adjustment only.
v1.0.1
Version 1.0.1
- No code or documentation changes detected in this release.
- Content of SKILL.md remains identical to the previous version.
v1.0.0
Initial Python implementation adds image editing and improves usability.
- Replaces shell script with Python for image generation and editing
- Adds support for image-to-image (editing: --input-image) in addition to text-to-image
- Allows custom output directory with --output-dir
- Updates key/env variable handling; now reads OPENROUTER_KEY
- Enhances prompt and filename handling, and modernizes usage examples
- Deprecates the previous shell workflow (generate_image.sh)
元数据
常见问题
nano-banana-pro-openrouter 是什么？
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter. Use for image create/modify requests incl. edits. Supports text-to-image + ima... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 171 次。
如何安装 nano-banana-pro-openrouter？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nanobananapro-openrouter」即可一键安装，无需额外配置。
nano-banana-pro-openrouter 是免费的吗？
是的，nano-banana-pro-openrouter 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
nano-banana-pro-openrouter 支持哪些平台？
nano-banana-pro-openrouter 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 nano-banana-pro-openrouter？
由 chang（@liberalchang）开发并维护，当前版本 v1.0.3。
推荐 Skills