🎬 Ai — AI

v1.0.0

在线视频生成使用此技能将文本或图像转为 AI 生成视频。支持 MP4、MOV、JPG、PNG，文件最大 200MB。营销人员、内容创作者、小企业……

0· 17·0 当前·0 累计

by @vcarolxhberger

文件处理开发工具视频处理图像处理系统工具

下载技能包

最后更新

2026/4/19

安全扫描

VirusTotal

无害

查看报告

OpenClaw

可疑

medium confidence

该技能主要充当第三方视频服务的 API 客户端（需提供 NEMO_TOKEN），但安装前请注意存在轻微不一致及隐私/暴露面问题。

评估建议

Things to consider before installing or using this skill: - It uploads your text, images, and any files you give it to a third‑party service at mega-api-prod.nemovideo.ai. Do not send private or sensitive content unless you trust that service and its privacy/terms. - The skill will use NEMO_TOKEN if present (store it in your environment if you want to use your account). If you don't provide one it will obtain an anonymous 7‑day token by POSTing a generated client UUID — this still tells the serv...

详细分析 ▾

✓ 用途与能力

The name/description (generate videos from text/images) matches the runtime instructions: calls a remote API, uploads files, creates render jobs and returns download URLs. Requesting a single API token (NEMO_TOKEN) is appropriate for this purpose.

ℹ 指令范围

Instructions are detailed and remain within the stated purpose (auth, session creation, SSE message streaming, upload, render/export polling). However the SKILL.md asks to 'auto-detect' an install path to set X-Skill-Platform and the frontmatter references a config path (~/.config/nemovideo/). That suggests the agent may inspect filesystem paths or environment to populate headers/config — an action not strictly needed to call the API and not declared consistently elsewhere. Also the instructions make it explicit that user files will be uploaded to a third‑party API, so privacy of uploaded content is an important consideration.

✓ 安装机制

This is an instruction-only skill with no install spec and no code files, so nothing will be downloaded or written to disk by an installer. That minimizes supply‑chain risk.

ℹ 凭证需求

The only declared required credential is NEMO_TOKEN (primaryEnv), which is proportional for an API client. Two small issues: (1) the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) that is not listed in the registry 'Required config paths' field — inconsistent declarations; (2) if NEMO_TOKEN is absent the skill instructs generating and exchanging an anonymous client UUID to obtain a token — this is expected behavior but it still sends a client identifier to a third‑party endpoint. No other unrelated secrets are requested.

✓ 持久化与权限

always:false and no install script means the skill is not forcing permanent inclusion or elevated platform privileges. It does not request to modify other skills or system settings.

安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/4/19

AI Video Generation Online — 初始版本 - 通过文本提示或图片生成 AI 视频（支持 MP4、MOV、JPG、PNG，最大 200MB）。 - 云端极速渲染（1–2 分钟）输出 1080p MP4，适合营销人员与内容创作者。 - 如需，自动认证并赠送免费 starter token；会话管理无缝衔接。 - 支持上传、时间轴编辑、预览、导出及余额/积分查询。 - 通过自然语言指令处理文件、文本、画幅、叠加层与音频。 - 完整错误处理与状态更新，常见问题即时反馈。

● 无害

安装命令

点击复制

官方npx clawhub@latest install ai-video-generation-online

镜像加速npx clawhub@latest install ai-video-generation-online --registry https://cn.longxiaskill.com镜像同步中

需要定制？告诉我你的需求 →

技能文档

快速开始

把文本或图片发给我，AI 视频即刻开工。也可直接描述需求。

试试说：

“把这段脚本或三张商品图生成 1080p MP4”
“按这段商品描述做 30 秒推广视频”
“无需拍摄，用文本或图片给营销人、创作者、老板出片”

连接后端

处理请求前先连 API，状态提示“连接中…”。 若环境变量已有 NEMO_TOKEN，直接建会话。否则获取免费试用 token：

生成 UUID 作为 clientId
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token，带 X-Client-Id
返回含 100 积分、7 天有效的 token，记为 NEMO_TOKEN

接着创建会话： POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent Bearer 授权，body {"task_name":"project","language":"en"} 响应中的 session_id 后续全程使用。告诉用户“已就绪”，技术细节不展示。

# AI Video Generation Online — 文本或图片一键生成视频把文本/图片发给我，并描述想要的效果。 AI 在远程 GPU 节点渲染，本机零安装。示例：上传脚本或三张商品图，输入“按商品描述做 30 秒推广视频”，约 1-2 分钟返回 1080p MP4，全程云端完成。提示越短越具体，视频越精准。

意图路由

用户提及 ai video generation online、画幅、文字层、音轨等，按关键词分派：

| 用户说法 | 动作 | 跳过 SSE？ | |-------------|--------|----------| | “export/导出/download/发我视频” | → §3.5 导出 | ✅ | | “credits/积分/balance/余额” | → §3.3 积分 | ✅ | | “status/状态/show tracks” | → §3.4 状态 | ✅ | | “upload/上传/发文件” | → §3.2 上传 | ✅ | | 其余（生成、编辑、加 BGM…） | → §3.1 SSE | ❌ |

云端渲染细节

导出任务排队到 GPU 节点，合成图层、H.264 压缩、最高 1080×1920，30-90 秒返回下载链接。会话 token 携带任务 ID，提前关标签页会导致任务孤立。

所有请求必须带： Authorization: Bearer X-Skill-Source: ai-video-generation-online X-Skill-Version: 1.0.0 X-Skill-Platform: clawhub/cursor/unknown 缺失则 402 失败。

API 概览

基地址: https://mega-api-prod.nemovideo.ai
建会话: POST /api/tasks/me/with-session/nemo_agent
SSE 对话: POST /run_sse，Accept: text/event-stream，最长 15 分钟
上传: POST /api/upload-video/nemo_agent/me/，支持文件或 URL
积分: GET /api/credits/balance/simple
状态: GET /api/state/nemo_agent/me//latest
导出: POST /api/render/proxy/lambda，轮询 / 至 status=completed，得 output.url

支持格式：mp4

数据来源：ClawHub ↗ · 中文优化：龙虾技能库