首页 / 技能 / Ai — AI

🎬 Ai — AI

v1.0.0

AI Video Maker 无需学习专业剪辑软件。只需描述需求——把我的图片变成一段带音乐和转场的30秒宣传视频——a...

0· 18·0 当前·0 累计
imo14reifey 头像by @imo14reifey
网络工具开发工具视频处理图像处理音频处理
下载技能包
最后更新
2026/4/19
0
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
medium confidence
该技能的需求与运行时指令大体上与云端 AI 视频创作服务一致，但在安装前，请留意少量元数据/指令不一致之处及隐私考量。
评估建议
This instruction-only skill appears to do what it says: upload your images/clips to nemovideo.ai and return rendered video URLs. Before installing or using it, consider: (1) Privacy: any files you upload will be sent to https://mega-api-prod.nemovideo.ai—do not upload sensitive or private data unless you trust that service and have reviewed its privacy/terms. (2) Credentials: the skill needs NEMO_TOKEN (you can set your own token or let it obtain an anonymous token); avoid supplying unrelated se...
详细分析 ▾
✓ 用途与能力
The skill claims to create videos from uploaded images/clips using a cloud backend and only requires a single service credential (NEMO_TOKEN). That credential and the described API calls align with the stated purpose (upload files, create sessions, render jobs).
ℹ 指令范围
SKILL.md provides explicit API flows: check env NEMO_TOKEN, otherwise obtain an anonymous token, create a session, upload files, stream SSE messages, poll render status, and return download URLs. These instructions stay within the stated video-creation purpose. They include a small extra behavior: deriving an X-Skill-Platform header from an install path (~/.clawhub/, ~/.cursor/skills/) which implies the agent may inspect its installation path or common directories to set headers — not strictly necessary for core functionality but not highly sensitive. The skill repeatedly instructs not to expose raw tokens to users.
✓ 安装机制
There is no install spec and no code files; the skill is instruction-only. This minimizes disk-write risk and matches the expected low install risk for an API-integration skill.
ℹ 凭证需求
Requires a single service credential (NEMO_TOKEN) which is appropriate for an API-backed video service. SKILL.md also documents an anonymous-token flow if no token is present. One inconsistency: SKILL.md frontmatter lists a configPaths value (~/.config/nemovideo/), but the registry metadata reported no required config paths — this mismatch should be clarified because the config path would allow the skill to access files under that directory if implemented.
✓ 持久化与权限
The skill is not marked always:true and is user-invocable (normal). It does not request system-wide persistence or elevated privileges. The only subtlety is the header that may be derived from an install path, which could require checking common user paths — a low-privilege read operation if performed.
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 Maker 1.0.0 — 初始版本 - 用 AI 即时将图片或片段生成宣传视频，无需手动剪辑 - 支持上传 MP4、MOV、JPG、PNG，单文件最大 500MB - 自动创建项目/会话，新用户赠送 100 积分 - 一键导出 1080p MP4，云端快速处理完成后提供下载链接 - 内置工作流：快速剪辑、迭代优化、批量项目 - 处理过程友好报错，状态以纯文本实时更新

● 无害

安装命令

点击复制
官方npx clawhub@latest install ai-ai-video-maker
镜像加速npx clawhub@latest install ai-ai-video-maker --registry https://cn.longxiaskill.com

技能文档

快速开始

把图片或片段发给我，AI 立即开始生成视频。也可以直接说想法。
试试这样说：
  • “create my images or clips”
  • “export 1080p MP4”
  • “turn my images into a 30-second”

一键初始化

本技能连接云端渲染后端。首次使用自动完成配置并提示“Connecting...”。 Token 检查：先找环境变量 NEMO_TOKEN。若存在，直接进入会话；否则：
  • 生成 UUID 作为客户端 ID
  • POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token，带 X-Client-Id 头
  • 取响应 data.token 即为 NEMO_TOKEN（100 免费积分，7 天有效期）

会话：POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent，Bearer 鉴权，body {"task_name":"project"}，保存返回的 session_id。配置完成提示“Ready!”。不向用户暴露 token 或原始 API 输出。

# AI Video Maker — 用图片一键生成视频 把图片或片段拖进对话框，告诉我需求即可。云端 GPU 完成渲染，本地无需安装任何软件。 典型流程：上传 5 张产品图 + 1 个 logo，说“turn my images into a 30-second promo video with music and transitions”，1-2 分钟后即可下载 1080p MP4。图片少于 10 张时，处理时间通常 <1 分钟。

指令映射

用户提到 ai ai video maker、aspect ratio、text overlays、audio tracks 等关键词，系统按意图路由到对应动作。

| 用户说法 | 动作 | 跳过 SSE？ | |-------------|--------|----------| | “export” / “导出” / “download” / “send me the video” | → §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” / 用户发文件 | → §3.2 上传 | ✅ | | 其他（generate、edit、加背景音乐…） | → §3.1 SSE | ❌ |

云端渲染流程

每次导出任务在云端 GPU 节点排队，合成视频层、应用平台级压缩（H.264，最高 1080×1920），30-90 秒内返回下载链接。会话 token 携带渲染任务 ID，关闭标签页会导致任务孤儿。 所有请求需带 Authorization: Bearer 及三个头：
  • X-Skill-Source: ai-ai-video-maker
  • X-Skill-Version: 1.0.0
  • X-Skill-Platform: clawhub|cursor|unknown（根据安装路径自动检测）
缺头返回 402。

API 基址：https://mega-api-prod.nemovideo.ai

  • 创建会话：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（免费）：POST /api/render/proxy/lambda，轮询 GET 直至 status=completed，下载地址在 output.url
支持格式：mp4、mov、avi、webm、mkv、jpg、png、gif、webp、mp3、wav、m4a、aac。

数据来源：ClawHub ↗ · 中文优化：龙虾技能库