← 返回 Skills 市场
Video Models
作者
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
123
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-models
功能描述
Turn a 60-second product demo clip into 1080p AI-processed videos just by typing what you need. Whether it's applying AI video models to transform or enhance...
安全使用建议
This skill appears to do what it says: it uploads video clips to a cloud render service using a single service token (NEMO_TOKEN) and returns processed video URLs. Before installing: (1) confirm you trust the backend domain (https://mega-api-prod.nemovideo.ai) and the skill author, since uploaded media and account credits can be accessed with NEMO_TOKEN; (2) clarify the metadata mismatch about ~/.config/nemovideo/ (does the skill try to read local config files?); (3) avoid supplying NEMO_TOKEN for accounts holding sensitive content or large billing privileges — consider using a scoped/test account or the anonymous token flow; (4) expect that any file you direct the skill to process will be transmitted to the remote API; (5) if you need stronger assurance, ask the publisher for a homepage, privacy policy, or source code before use.
功能分析
Type: OpenClaw Skill
Name: video-models
Version: 1.0.0
The video-models skill is a functional integration for an AI video processing service (nemovideo.ai). It provides instructions for the agent to manage authentication via environment variables or anonymous tokens, handle file uploads, and poll for video rendering status. The network activity and session management are consistent with the stated purpose of the tool, and no indicators of data exfiltration, malicious execution, or deceptive prompt injection were identified.
能力评估
Purpose & Capability
Name/description match the requested credential (NEMO_TOKEN) and the described API endpoints. No unrelated binaries, services, or credentials are requested.
Instruction Scope
SKILL.md stays within the domain of uploading videos, creating sessions, polling render status, and returning download URLs. It instructs using multipart uploads or URL uploads and handling SSE streams. Two points to note: (1) the frontmatter metadata declares a config path (~/.config/nemovideo/) which suggests the skill might read a local config, but the registry metadata lists no required config paths — this mismatch should be clarified; (2) the runtime instructions allow uploading local files (expected) — ensure the agent only uploads user-provided media and not arbitrary local files.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest installer risk (nothing is written to disk by an installer).
Credentials
Only NEMO_TOKEN is required, which is proportionate for a third-party cloud video service. However, that token grants account-level access (credits, session state, and uploaded media) so it should only be provided for trusted accounts/services. The skill will also obtain anonymous tokens from the remote API if no NEMO_TOKEN is present.
Persistence & Privilege
always:false and user-invocable:true — the skill is not force-included. It does not request elevated platform-wide privileges in its instructions.
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-models - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-models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: Effortlessly apply AI video models to your clips and generate 1080p exports in under 2 minutes.
- Upload up to 500MB video files (mp4, mov, avi, webm, and more) and process with natural-language instructions.
- Automatic session handling and backend API connection with free starter credits for new users.
- Export, credits, upload, and other actions intelligently matched from user prompts.
- Transparent status updates — see connection, ongoing processing, and timeline changes.
- Streamlined workflow: upload → describe enhancement → download professionally processed video.
元数据
常见问题
Video Models 是什么？
Turn a 60-second product demo clip into 1080p AI-processed videos just by typing what you need. Whether it's applying AI video models to transform or enhance... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 123 次。
如何安装 Video Models？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-models」即可一键安装，无需额外配置。
Video Models 是免费的吗？
是的，Video Models 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Models 支持哪些平台？
Video Models 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 Models？
由 susan4731-wilfordf（@susan4731-wilfordf）开发并维护，当前版本 v1.0.0。
推荐 Skills