← 返回 Skills 市场
291
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install veo-skill
功能描述
Veo, Veo 3.1 Fast - Google AI video generation models for AI agents. 1080p HD output, reference image support, intelligent audio generation.
安全使用建议
This skill appears coherent: it documents how to call monet.vision and only asks for MONET_API_KEY. Before installing, verify monet.vision is the legitimate service you expect (the package metadata has no homepage/source link). Use a dedicated API key with minimal permissions and billing controls, confirm expected data retention (files reportedly stored 24 hours), and monitor API usage for unexpected calls. If you need vendor assurance, ask the skill author for a homepage or official docs link and confirm any 'Google' branding is accurate.
功能分析
Type: OpenClaw Skill
Name: veo-skill
Version: 1.0.0
The skill bundle is benign. All files consistently describe and provide examples for interacting with the `monet.vision` API for AI video generation. The `SKILL.md` and `README.md` files contain clear instructions and code snippets (curl, TypeScript) that exclusively target `https://monet.vision` and utilize a `MONET_API_KEY` for authentication, which is declared as a required environment variable. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts designed to mislead an AI agent into performing harmful actions beyond the stated purpose of video generation.
能力评估
Purpose & Capability
The skill describes Google 'Veo' models but the runtime instructions consistently call monet.vision API endpoints and only require MONET_API_KEY — which is coherent for a wrapper around Monet's video API. Minor concern: the registry metadata lists no homepage and source is unknown, and the marketing claim of 'Google' could be overstated; verify that monet.vision is the legitimate provider you expect.
Instruction Scope
SKILL.md is instruction-only and shows concrete curl/fetch examples that use only the declared MONET_API_KEY and standard HTTP endpoints (tasks, files). It does not instruct reading arbitrary local files or unrelated environment variables, nor does it transmit data to unexpected endpoints beyond monet.vision and files.monet.vision.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes on-disk risk; nothing is downloaded or executed by an installer.
Credentials
Only a single environment variable (MONET_API_KEY) is required, which is appropriate for calling a third-party API. No additional secrets, config paths, or unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request elevated persistence or modify other skills. Autonomous invocation is permitted (platform default) and is not by itself a concern here.
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 veo-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/veo-skill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: Veo and Veo 3.1 Fast video generation models
元数据
常见问题
Veo Skill 是什么？
Veo, Veo 3.1 Fast - Google AI video generation models for AI agents. 1080p HD output, reference image support, intelligent audio generation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 291 次。
如何安装 Veo Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install veo-skill」即可一键安装，无需额外配置。
Veo Skill 是免费的吗？
是的，Veo Skill 完全免费（开源免费），可自由下载、安装和使用。
Veo Skill 支持哪些平台？
Veo Skill 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 Skill？
由 seekton（@seekton）开发并维护，当前版本 v1.0.0。
推荐 Skills