← 返回 Skills 市场
Video Toolkit
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
107
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-toolkit
功能描述
Get edited 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 th...
安全使用建议
This skill appears to do what it claims: it uploads videos to a remote editing API and returns rendered files. Before installing, consider: (1) Privacy — your video files are sent to https://mega-api-prod.nemovideo.ai; avoid uploading sensitive content unless you trust the service and its privacy terms. (2) Credential scope — it requests a single NEMO_TOKEN; if you set a long-lived token, treat it like a password. The skill can also obtain a short anonymous token for you. (3) Minor unexplained metadata — the skill metadata lists ~/.config/nemovideo/ though SKILL.md doesn't say the agent will access that path; ask the publisher why if you are concerned. (4) Verify the service domain and organization (no homepage provided here) if you need stronger trust assurances. If you are comfortable with those privacy/legitimacy points, the skill’s behavior is coherent with its stated purpose.
功能分析
Type: OpenClaw Skill
Name: video-toolkit
Version: 1.0.0
The video-toolkit skill is a legitimate integration for a cloud-based video editing service (nemovideo.ai). It provides detailed instructions for an AI agent to manage video processing tasks, including session authentication, file uploads, and polling for render results. The skill uses specific, limited permissions (NEMO_TOKEN environment variable and a dedicated ~/.config/nemovideo/ directory) and communicates exclusively with the stated service domain (mega-api-prod.nemovideo.ai). No evidence of data exfiltration, unauthorized command execution, or malicious prompt injection was found.
能力评估
Purpose & Capability
The skill name and description match the actions described in SKILL.md: creating sessions, uploading video files, streaming SSE edits, and exporting rendered MP4s. Requested primary credential (NEMO_TOKEN) is appropriate for a hosted editing API. Small inconsistency: the metadata declares a required config path (~/.config/nemovideo/) but the runtime instructions do not describe reading or writing that path. This may be benign (client libraries sometimes store state there) but is not explained in the instructions.
Instruction Scope
SKILL.md confines runtime actions to: generating/using an API token, creating a session, uploading user-provided media, reading SSE events, polling export status, and returning download URLs. It does not instruct reading arbitrary local files or unrelated environment variables. It does instruct sending user video files to the remote domain (mega-api-prod.nemovideo.ai), which is expected for this service but is a privacy consideration.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest installation risk. Nothing is downloaded or written to disk by an installer in the skill bundle itself.
Credentials
Only NEMO_TOKEN is required (declared as primaryEnv) — proportionate for a hosted API. The metadata's configPaths entry (~/.config/nemovideo/) is additional surface area that isn't justified in the SKILL.md; if the agent will access that path it should be documented. The skill also explains how to obtain a temporary anonymous token if NEMO_TOKEN isn't present, which is consistent with needing one token.
Persistence & Privilege
always:false and default model invocation behavior are used. The skill does not request elevated platform privileges or modification of other skills or system-wide config. It stores ephemeral session_id and uses bearer tokens as typical for a hosted service.
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-toolkit - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-toolkit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
Video Toolkit 1.0.0 — Initial Release
- Instantly edit and export your videos online (MP4, MOV, AVI, WebM, up to 500MB).
- Simple workflow: upload video, describe edits (e.g. trim silences, add captions), and receive a 1080p MP4 download.
- No video editing software or manual configuration required — all processing is cloud-powered.
- Tracks session state, credits, and progress; supports status updates and troubleshooting.
- Automatic handling of authentication, session creation, and error cases for a smooth user experience.
元数据
常见问题
Video Toolkit 是什么？
Get edited 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 th... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 107 次。
如何安装 Video Toolkit？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-toolkit」即可一键安装，无需额外配置。
Video Toolkit 是免费的吗？
是的，Video Toolkit 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Toolkit 支持哪些平台？
Video Toolkit 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 Toolkit？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills