← 返回 Skills 市场
Video App
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
49
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-app
功能描述
Get polished MP4 files ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim...
安全使用建议
This skill appears to be a front-end for a cloud video-editing service (mega-api-prod.nemovideo.ai) and only requires a NEMO_TOKEN to operate — that's expected. Before installing or using it: 1) Confirm you trust the nemovideo.ai domain and the skill owner, because uploaded video files will be sent to that backend and may contain sensitive content. 2) Ask the publisher to explain the metadata mismatch: SKILL.md mentions a config path (~/.config/nemovideo/) but the registry summary says none — clarify whether the skill will read that directory. 3) Decide whether you are comfortable with the skill probing install paths (it will derive X-Skill-Platform from locations like ~/.clawhub/ or ~/.cursor/skills/), which reveals presence of other tooling. 4) Prefer using an explicit, limited token (or anonymous token) and avoid exposing long-lived credentials; review what the skill logs or returns to users. 5) If you need higher assurance, request source or homepage, or run network/FS monitoring during an initial test to confirm behavior matches these instructions.
功能分析
Type: OpenClaw Skill
Name: video-app
Version: 1.0.0
The video-app skill is a legitimate integration for a cloud-based video editing service (nemovideo.ai). It manages video processing workflows including file uploads, session management, and rendering via standard API calls to mega-api-prod.nemovideo.ai. The instructions in SKILL.md are transparent, align with the stated purpose of AI-assisted video editing, and include security-conscious directives such as preventing the exposure of API tokens to the end-user.
能力评估
Purpose & Capability
The name/description (cloud video editing) matches the actions (upload, render, export via mega-api-prod.nemovideo.ai) and the only declared credential is NEMO_TOKEN, which is expected. However the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) that is not reflected in the registry summary's 'Required config paths: none' — an inconsistency that may indicate the skill expects access to a user config directory.
Instruction Scope
The runtime instructions tell the agent to check the environment for NEMO_TOKEN and, if missing, generate an anonymous token by POSTing to the service (including generating a UUID client id). They also instruct adding attribution headers and deriving X-Skill-Platform from the agent's install path (~/.clawhub/, ~/.cursor/skills/, otherwise 'unknown'). Detecting the install path or reading a config directory implies filesystem probing beyond simply uploading video files. The skill also mediates SSE streams and polls state. None of that is intrinsically malicious, but the instructions give the agent permission to read environment/install-path context and to call external endpoints — verify you trust the service and that reading those paths is acceptable.
Install Mechanism
There is no install spec and no code files — instruction-only skill — so nothing is written to disk by the skill itself. This is the lowest-risk install mechanism.
Credentials
Only NEMO_TOKEN is declared as a required env var (primary credential), which is proportional for a cloud API. But the SKILL.md frontmatter's metadata lists a configPaths entry that implies the skill might access ~/.config/nemovideo/ (not shown in the registry summary). That mismatch should be clarified: does the skill actually need to read that path?
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent 'always' presence. It creates ephemeral session tokens and may orphan jobs if a session is closed, but it does not request elevated platform privileges in the manifest.
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-app - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-app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 App — Edit and Export Videos Fast.
- Upload and edit MP4, MOV, AVI, and WebM video files up to 500MB with natural language instructions (e.g., "trim the silent parts, add background music, and export in 1080p").
- Automatic setup with seamless cloud connection and session creation; 100 free credits for first-time users.
- Fast GPU-accelerated cloud processing with 1080p MP4 export—most clips process in 1–2 minutes.
- Simple workflows for quick edits, batch processing, and iterative refinements.
- Supports tracking credits, querying export/state, and giving concise status updates.
元数据
常见问题
Video App 是什么？
Get polished MP4 files ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 49 次。
如何安装 Video App？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-app」即可一键安装，无需额外配置。
Video App 是免费的吗？
是的，Video App 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video App 支持哪些平台？
Video App 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 App？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills