← 返回 Skills 市场
Vidu Ai
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
54
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install vidu-ai
功能描述
Turn a short text prompt or a single reference image into 1080p AI generated clips just by typing what you need. Whether it's generating short video clips fr...
安全使用建议
This skill is coherent with a cloud video generation service: it will contact mega-api-prod.nemovideo.ai, upload media, and use/obtain a short-lived NEMO_TOKEN if you don't provide one. Before installing, consider: (1) privacy — uploaded images/videos and prompts are sent to a third‑party service; avoid sensitive content, (2) token handling — the skill may obtain and store a 7‑day anonymous token for you, so ask where that token/session is stored if you need persistence control, (3) clarify the config path: the SKILL.md references ~/.config/nemovideo/ but registry metadata didn't list it — confirm whether the skill will read/write files there, and (4) review the service's privacy/terms on the provider domain if possible. If you need higher assurance, request the author to resolve the configPath mismatch and to confirm whether tokens/session data are only kept in ephemeral agent state or written to disk.
功能分析
Type: OpenClaw Skill
Name: vidu-ai
Version: 1.0.0
The skill provides a functional interface for the Vidu AI video generation service. It manages authentication via the NEMO_TOKEN environment variable or an anonymous token generation flow, and communicates exclusively with the 'mega-api-prod.nemovideo.ai' backend. The instructions in SKILL.md are focused on session management, file uploads, and interpreting server-sent events (SSE) for video rendering. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力评估
Purpose & Capability
Name/description (AI video generation) align with requested network endpoints and the single credential NEMO_TOKEN. The skill's API calls, upload endpoints, and render flow are coherent with a cloud video-rendering service.
Instruction Scope
SKILL.md instructs the agent to obtain an anonymous token if NEMO_TOKEN is absent, create sessions, upload files, stream SSE, poll job status, and include attribution headers by reading the skill frontmatter and detecting install path. Those actions are expected for this service, but the skill also declares a config path (~/.config/nemovideo/) in its YAML frontmatter while the registry metadata lists no required config paths — a minor inconsistency to clarify. Instructions explicitly tell the agent not to display raw tokens/responses, which is appropriate.
Install Mechanism
Instruction-only skill with no install spec or downloaded code. Lowest-risk class: nothing is written to disk by an installer in the package metadata itself.
Credentials
Only one credential (NEMO_TOKEN) is required, which is appropriate for a third‑party API. The skill will also generate an anonymous token automatically if none is provided — reasonable but means the agent will POST to the remote auth endpoint and hold a short-lived token (7 days). The frontmatter's config path (~/.config/nemovideo/) suggests possible optional local storage but registry metadata did not list required config paths; clarify whether the skill will read/write that path.
Persistence & Privilege
always:false and normal autonomous invocation. The skill asks to store a session_id for the active session (expected in-memory or agent state) but does not request persistent system-wide privileges or modification of other skills.
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 vidu-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/vidu-ai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 of Vidu AI skill.
- Generate 1080p video clips from text prompts or images in 30-90 seconds.
- Automatic authentication and session management with 7-day free trial tokens.
- Upload support for common video, image, and audio file formats (max 200MB).
- Cloud rendering pipeline; returns downloadable MP4s with no need for local setup.
- Supports timeline edits, credits checking, state viewing, and export actions via natural language.
- Handles error codes, session timeouts, and re-authentication automatically.
元数据
常见问题
Vidu Ai 是什么？
Turn a short text prompt or a single reference image into 1080p AI generated clips just by typing what you need. Whether it's generating short video clips fr... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 54 次。
如何安装 Vidu Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vidu-ai」即可一键安装，无需额外配置。
Vidu Ai 是免费的吗？
是的，Vidu Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Vidu Ai 支持哪些平台？
Vidu Ai 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 Vidu Ai？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills