← 返回 Skills 市场
Video Editing Classes
作者
susan4731-wilfordf
· GitHub ↗
· v1.0.0
· MIT-0
53
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-editing-classes
功能描述
Get edited tutorial clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something li...
安全使用建议
This skill appears to do what it says: it uploads your video and controls a cloud rendering service (mega-api-prod.nemovideo.ai) using a single NEMO_TOKEN (or an automatically obtained anonymous token). Before installing or using it, consider:
- Privacy/ownership: your uploaded footage is sent to a third-party service. Don’t upload sensitive or private footage unless you trust their handling and retention policies. Ask for the service's privacy policy and data retention terms.
- Tokens: you can supply your own NEMO_TOKEN to avoid anonymous token creation; otherwise the skill will call the API to mint a 7-day anonymous token. If you prefer, provide a token you control and revoke it when done.
- Attribution and local reads: the skill will read its own frontmatter and may inspect install paths to set an X-Skill-Platform header — this is limited but means the agent may check certain paths.
- Network traffic: all operations contact https://mega-api-prod.nemovideo.ai. If you need higher assurance, verify the domain/operator (homepage, repo, privacy policy) before uploading content.
What would raise confidence: a known homepage or source repository, published privacy/security docs, or an operator identity and terms of service for nemovideo.ai. If you cannot verify the service, avoid uploading sensitive content and consider providing a scoped service token you can revoke.
功能分析
Type: OpenClaw Skill
Name: video-editing-classes
Version: 1.0.0
The skill is a legitimate wrapper for a cloud-based video editing service (nemovideo.ai). It manages session tokens, handles file uploads, and processes video editing commands via standard REST API calls. While it includes logic to detect the host platform by checking installation paths (e.g., ~/.clawhub) for telemetry headers, this behavior is transparently documented and aligned with the stated purpose of the tool.
能力评估
Purpose & Capability
The name/description (cloud video editing, upload raw footage, export MP4) align with the instructions (upload endpoint, render/export workflow). The single required credential (NEMO_TOKEN) matches the described cloud backend. Minor inconsistency: the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) and install-path detection for attribution headers, but the registry metadata provided earlier did not declare required config paths — this is a small mismatch but does not contradict the stated purpose.
Instruction Scope
SKILL.md provides explicit runtime steps that stay within video-editing operations: check for NEMO_TOKEN, create an anonymous token via POST to the service if missing, create sessions, upload media, use SSE for edits, and request exports. These instructions will cause the agent to transmit uploaded videos and metadata to https://mega-api-prod.nemovideo.ai. The skill also instructs the agent to read its own YAML frontmatter and inspect install paths to set an X-Skill-Platform header — that implies some local filesystem inspection (install-path detection) but is scoped to attribution rather than unrelated secrets.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing new is written to disk by an installer. This is the lowest-risk install mechanism in the platform model.
Credentials
Only one credential is requested (NEMO_TOKEN) which is appropriate for a single third-party editing backend. The skill will also generate an anonymous token by calling the service if NEMO_TOKEN is not present (and then use that token). There are no unrelated secrets requested. The small mismatch between the declared registry configPaths (none) and the SKILL.md metadata (~/.config/nemovideo/) is worth noting but not proof of malicious intent.
Persistence & Privilege
always:false and no install-time persistence is requested. The skill uses ephemeral session_id tokens for render jobs; it does not ask to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not combined with 'always:true' or broad credential access.
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-editing-classes - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-editing-classes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 Editing Classes skill.
- Upload raw video files (up to 500MB) and request edits like trimming pauses, adding transitions, or overlaying text labels.
- No local installation required; editing and export happen on a cloud backend with GPU acceleration.
- Automatic account setup and 100 free credits for new users; manage credits and session directly in chat.
- Supports multiple video, audio, and image formats; outputs 1080p MP4 ready for download.
- Handles common workflows: quick edits, batch processing, and iterative refinements with stateful sessions.
元数据
常见问题
Video Editing Classes 是什么？
Get edited tutorial clips ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something li... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 53 次。
如何安装 Video Editing Classes？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-editing-classes」即可一键安装，无需额外配置。
Video Editing Classes 是免费的吗？
是的，Video Editing Classes 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Editing Classes 支持哪些平台？
Video Editing Classes 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 Editing Classes？
由 susan4731-wilfordf（@susan4731-wilfordf）开发并维护，当前版本 v1.0.0。
推荐 Skills