← 返回 Skills 市场
Veo 3.1
作者
NanoPhoto.AI
· GitHub ↗
· v1.0.0
· MIT-0
192
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install nanophoto-veo-3-1
功能描述
Generate videos with the NanoPhoto.AI Veo 3.1 API. Use when: (1) User wants Veo 3.1 text-to-video generation, (2) User wants Veo 3.1 generation from referenc...
安全使用建议
This skill appears to do only what it says: submit shots to NanoPhoto's Veo 3.1 API and poll for status. Before installing: (1) ensure you're comfortable sending prompts and any image URLs to nanophoto.ai (image-based modes require public URLs), (2) store the API key in the platform's secure env setting rather than pasting it into chat, and (3) be aware the script will read ~/.openclaw/openclaw.json to resolve a saved key — make sure that file contains only appropriate data. If you need higher assurance, verify the API key management page on the vendor site and review the included script yourself.
功能分析
Type: OpenClaw Skill
Name: nanophoto-veo-3-1
Version: 1.0.0
The skill provides a legitimate interface for the NanoPhoto.AI Veo 3.1 video generation API. The Python script (scripts/veo_3_1.py) uses standard libraries to handle API requests and polling, with credential resolution limited to the specific NANOPHOTO_API_KEY and a documented configuration file (~/.openclaw/openclaw.json). No evidence of data exfiltration, malicious execution, or prompt injection was found across the code or documentation.
能力评估
Purpose & Capability
Name/description match behavior: the bundled script only calls nanophoto.ai's Veo endpoints and implements text/reference/first-last-frame workflows. The only required credential is NANOPHOTO_API_KEY, which is appropriate for the stated API calls.
Instruction Scope
SKILL.md and the script confine operations to building shot payloads, POSTing to the generate/check-status endpoints, and optionally polling. The only local file read is the OpenClaw config (~/.openclaw/openclaw.json) to resolve a stored API key, which the docs explicitly declare.
Install Mechanism
No install spec; skill is instruction-only with a bundled Python script that uses the standard library for HTTP. Nothing is downloaded or written by an installer.
Credentials
Requires exactly one environment variable (NANOPHOTO_API_KEY). The script accepts an explicit --api-key override and falls back to environment or the declared OpenClaw config path; no other secrets or unrelated env vars are requested.
Persistence & Privilege
always is false and the skill does not request permanent system-wide changes or modify other skills. It can be invoked autonomously (platform default), which is expected for an integration skill.
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 nanophoto-veo-3-1 - 安装完成后，直接呼叫该 Skill 的名称或使用
/nanophoto-veo-3-1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
v1.0.0
Initial release. Generate Veo 3.1 videos with text-to-video, reference-image, and first/last-frame workflows. Supports multi-shot jobs up to 21 shots, 720p/1080p/4k resolution rules, status checks, and optional in-process polling from a single compliant script.
元数据
常见问题
Veo 3.1 是什么？
Generate videos with the NanoPhoto.AI Veo 3.1 API. Use when: (1) User wants Veo 3.1 text-to-video generation, (2) User wants Veo 3.1 generation from referenc... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 192 次。
如何安装 Veo 3.1？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nanophoto-veo-3-1」即可一键安装，无需额外配置。
Veo 3.1 是免费的吗？
是的，Veo 3.1 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Veo 3.1 支持哪些平台？
Veo 3.1 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 Veo 3.1？
由 NanoPhoto.AI（@nanophotohq）开发并维护，当前版本 v1.0.0。
推荐 Skills