← 返回 Skills 市场
Video Generative Ai
作者
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
86
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-generative-ai
功能描述
Get AI generated videos ready to post, without touching a single slider. Upload your text or images (MP4, MOV, PNG, JPG, up to 200MB), say something like "ge...
安全使用建议
This skill appears to do what it says: it talks to a remote nemovideo.ai API to generate videos and only needs a NEMO_TOKEN. Before installing: (1) Confirm you trust https://mega-api-prod.nemovideo.ai and review its privacy/terms—your uploaded media and prompts are sent to that remote service. (2) Clarify the metadata mismatch about ~/.config/nemovideo/ (the skill frontmatter references it even though the registry summary did not). (3) Use a limited-scope or ephemeral token (or rely on the anonymous-token flow) rather than a highly privileged account token. (4) Avoid uploading sensitive or private content to this service. (5) If you need stronger assurance, ask the publisher for a homepage/privacy policy or test with non-sensitive media and monitor network activity. If any of these checks fail or you can't verify the service, treat the skill as untrusted and do not provide long-lived credentials.
功能分析
Type: OpenClaw Skill
Name: video-generative-ai
Version: 1.0.0
The skill provides a standard interface for interacting with the NemoVideo AI service for video generation. It includes instructions for automated anonymous authentication, session management, and media processing via the mega-api-prod.nemovideo.ai backend. No indicators of data exfiltration, malicious code execution, or harmful prompt injection were found; the behavior is consistent with the stated purpose of AI video generation.
能力评估
Purpose & Capability
The name and description (AI video generation) align with the required credential (NEMO_TOKEN) and the SKILL.md which describes a cloud-render pipeline. Minor inconsistency: registry metadata earlier showed no required config paths, but the SKILL.md frontmatter metadata lists a config path (~/.config/nemovideo/). This mismatch should be clarified but doesn't imply malicious intent.
Instruction Scope
The instructions stay within the scope of a cloud video-generation client: check/use NEMO_TOKEN, obtain anonymous token if missing, create a session, upload media, stream SSE events, poll for export status, and download results. The skill asks to add attribution headers and to map GUI commands to API calls. It does not instruct reading unrelated system files or other environment secrets. One small note: it mentions auto-detecting X-Skill-Platform from the install path which may require access to the agent's environment/paths—this is plausible for attribution but should be explicit.
Install Mechanism
Instruction-only skill with no install spec and no code files—no files are written to disk by the skill itself. This is the lowest-risk install model.
Credentials
Only a single credential is requested (NEMO_TOKEN) and it is clearly the API bearer token needed to call the remote service. The SKILL.md also documents a safe fallback (anonymous-token endpoint) to obtain a short-lived token. No other unrelated credentials or secrets are requested.
Persistence & Privilege
always:false and the skill expects to hold a session_id for operations—this is appropriate for a remote render client. The skill does reference a config path in its frontmatter (possible local config usage), but it does not request system-wide privileges or modification of other skills' settings.
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 video-generative-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-generative-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
Video Generative AI skill initial release:
- Generate 1080p AI videos from text prompts or uploads (MP4, MOV, PNG, JPG, up to 200MB)
- No editing experience needed; production-ready videos in 1-3 minutes
- Cloud-based: supports quick setup with temporary or personal tokens (100 free credits for new users)
- Export videos in multiple formats (MP4, MOV, AVI, JPG, PNG, and more)
- Simple commands for upload, generation, export, balance, and status tracking
- Session and error handling designed for seamless, iterative workflows
元数据
常见问题
Video Generative Ai 是什么？
Get AI generated videos ready to post, without touching a single slider. Upload your text or images (MP4, MOV, PNG, JPG, up to 200MB), say something like "ge... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 86 次。
如何安装 Video Generative Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-generative-ai」即可一键安装，无需额外配置。
Video Generative Ai 是免费的吗？
是的，Video Generative Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Generative Ai 支持哪些平台？
Video Generative 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 Video Generative Ai？
由 dsewell-583h0（@dsewell-583h0）开发并维护，当前版本 v1.0.0。
推荐 Skills