← 返回 Skills 市场
Video Canva
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
58
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-canva
功能描述
Turn five product photos and a logo file into 1080p designed video files just by typing what you need. Whether it's building videos from images and clips usi...
安全使用建议
This skill will upload any images/clips you give it to a third‑party rendering service at mega-api-prod.nemovideo.ai and requires a NEMO_TOKEN (it can create a temporary anonymous token for you). Before installing/using: 1) confirm you trust the domain/service (no homepage or known owner is provided here), 2) avoid uploading sensitive content to an unknown service, 3) if you already have a NEMO_TOKEN, treat it like any API secret, and 4) ask the publisher to clarify the config-path reference (~/.config/nemovideo/) shown in the SKILL.md frontmatter. If you’re uncomfortable, don’t provide private files or credentials and request more provenance (homepage, owner info, or privacy policy).
功能分析
Type: OpenClaw Skill
Name: video-canva
Version: 1.0.0
The skill is a legitimate integration for a video editing service (nemovideo.ai). It defines standard API workflows for session management, file uploads, and cloud rendering. It includes instructions for the agent to handle authentication and attribution headers correctly without any evidence of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The name/description (create videos from images/clips) matches the runtime actions: creating sessions, uploading media, queuing render jobs and returning download URLs. Requesting a single service token (NEMO_TOKEN) and asking to POST to an API at mega-api-prod.nemovideo.ai is proportionate to a cloud render backend.
Instruction Scope
SKILL.md explicitly instructs the agent to check for NEMO_TOKEN, generate an anonymous token if missing (via an anonymous-token endpoint), create sessions, upload files, stream SSE responses, poll render status, and return download URLs. These operations are within the stated purpose. Minor scope items: it instructs auto-detection of an install path to set X-Skill-Platform (which may require reading agent install/config path) and references a local config path (~/.config/nemovideo/) in frontmatter — this is slightly outside pure upload/render steps but not a clear abuse.
Install Mechanism
No install spec or third-party packages are requested (instruction-only). Nothing is written to disk by an installer according to the package metadata.
Credentials
The skill declares a single primary credential (NEMO_TOKEN) which is consistent with a cloud API. The instructions also allow anonymously obtaining a temporary token. There is a small inconsistency: registry metadata listed no config paths, but the SKILL.md frontmatter references ~/.config/nemovideo/ — this should be clarified. Remember that NEMO_TOKEN grants access to upload and render operations on the remote service, so treat it like a service credential.
Persistence & Privilege
The skill is user-invocable, not always-enabled, and does not request elevated or system-wide privileges. It asks the agent to hold a session_id for the duration of operations, which is normal. There is no instruction to modify other skills or global agent configuration.
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-canva - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-canva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 Video Canva — Create Videos from Images and Clips.
- Instantly create 1080p videos from up to five product images and a logo using natural language prompts.
- Automatic cloud-based editing and export—no manual timeline editing or export settings required.
- Upload various media formats (video, image, and audio) up to 500MB; output as high-quality MP4.
- Smart prompt matching routes requests for export, credits, upload, and edits to appropriate cloud actions.
- Includes robust error handling, automatic token management, and session recovery for seamless user experience.
元数据
常见问题
Video Canva 是什么？
Turn five product photos and a logo file into 1080p designed video files just by typing what you need. Whether it's building videos from images and clips usi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 58 次。
如何安装 Video Canva？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-canva」即可一键安装，无需额外配置。
Video Canva 是免费的吗？
是的，Video Canva 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Canva 支持哪些平台？
Video Canva 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 Canva？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills