← 返回 Skills 市场
Video Workflow
作者
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
89
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-workflow
功能描述
edit raw video clips into polished edited clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it for...
安全使用建议
This skill appears to do what it says (upload your videos to a cloud service, edit them, and return a downloadable file), but take these precautions before installing or using it:
- Expect your local video files to be uploaded to https://mega-api-prod.nemovideo.ai. Do not upload sensitive or private footage until you trust the service and its privacy/retention policies.
- The skill will accept a NEMO_TOKEN if you provide one, but if you don't it will request an anonymous token from the service automatically; this means the skill will make outbound network calls even without you supplying credentials.
- The SKILL.md metadata mentions a config path (~/.config/nemovideo/) that is not declared elsewhere — ask the publisher whether the skill reads/writes files there and how tokens are stored or persisted.
- Because this is an instruction-only skill (no code shipped, no repo/source provided), you must trust the documented API endpoints and behavior. If possible, ask for the service homepage, privacy policy, or source code; verify the domain and ownership of nemovideo.ai.
- Test with a short, non-sensitive clip first to confirm behavior and outputs.
If the publisher can confirm (a) whether tokens are ever stored locally and where, (b) provide a privacy/retention policy for uploaded media, and (c) reconcile the configPaths metadata, my confidence in this assessment would increase.
功能分析
Type: OpenClaw Skill
Name: video-workflow
Version: 1.0.0
The video-workflow skill is a legitimate integration for a cloud-based video editing service (nemovideo.ai). The SKILL.md provides detailed instructions for the AI agent to manage authentication via environment variables or anonymous token generation, handle session-based video processing, and manage file uploads and exports. All network activity is directed to the service's production API (mega-api-prod.nemovideo.ai), and the requested access to configuration paths and environment variables is consistent with the stated purpose of video editing and rendering.
能力评估
Purpose & Capability
The name/description match the instructions: the skill uploads video files and calls a remote rendering API. Requesting a single NEMO_TOKEN credential is coherent for a cloud video service. However, the SKILL.md frontmatter includes a configPaths entry (~/.config/nemovideo/) while the registry metadata listed no required config paths — this mismatch is unexplained.
Instruction Scope
Runtime instructions explicitly tell the agent to read local file paths (uploads), call multiple endpoints at https://mega-api-prod.nemovideo.ai (auth, upload, SSE, render, export), and poll session state. Uploading user files to a third-party service is intrinsic to the advertised feature, but it is a privacy/exfiltration vector and should be expected. The SKILL.md also instructs the agent to auto-generate an anonymous token (network POST to /api/auth/anonymous-token) if NEMO_TOKEN is missing — this creates network activity even without a pre-provided credential. The metadata/configPaths discrepancy leaves unclear whether the skill will read or write to ~/.config/nemovideo/.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing is written to disk by an installer. This is the lowest install risk, but also means you must trust the instructions and remote endpoints the skill calls.
Credentials
Only a single credential (NEMO_TOKEN) is required, which aligns with a cloud video service. The skill will, however, attempt to acquire an anonymous token via a network call if no token is present — meaning it can operate without an explicit user-provided secret. The presence of the configPaths entry in SKILL.md metadata suggests possible access to a user config directory, which was not declared in the registry and is not justified in the instructions.
Persistence & Privilege
The skill does not request always:true and does not declare elevated platform privileges. Autonomous invocation is allowed (platform default). There is a small concern that the frontmatter implies a config path that could be used to persist tokens or config under ~/.config/nemovideo/ — the SKILL.md does not clearly state whether it will store the anonymous token locally.
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-workflow - 安装完成后,直接呼叫该 Skill 的名称或使用
/video-workflow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 with streamlined cloud-based video editing and export.
- Edit raw MP4, MOV, AVI, or WebM clips (up to 500MB) into polished videos using cloud GPUs.
- Simple setup: automatic anonymous account creation with free credits and session management.
- Supports upload, batch process, timeline edits, and export to 1080p MP4.
- User instructions mapped to backend actions; status and error handling built in.
- Export, credits, status, and uploads supported via keyword routing for quick workflow.
元数据
常见问题
Video Workflow 是什么?
edit raw video clips into polished edited clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it for... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 89 次。
如何安装 Video Workflow?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-workflow」即可一键安装,无需额外配置。
Video Workflow 是免费的吗?
是的,Video Workflow 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Video Workflow 支持哪些平台?
Video Workflow 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 Workflow?
由 dsewell-583h0(@dsewell-583h0)开发并维护,当前版本 v1.0.0。
推荐 Skills