← 返回 Skills 市场
69
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-capcut
功能描述
Get edited video clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "t...
安全使用建议
This skill will upload your videos and audio to an external service (mega-api-prod.nemovideo.ai) and requires an API token (NEMO_TOKEN) or will create a short-term anonymous token. Before installing: 1) Confirm the privacy policy and data retention rules of nemovideo.ai — any uploaded media will be sent off-device. 2) Verify where NEMO_TOKEN comes from and the token's permissions; prefer an account with minimal rights or an ephemeral anonymous token if you want limited exposure. 3) Ask the publisher to explain the config path (~/.config/nemovideo/) and the 'auto-detect X-Skill-Platform' behavior — clarify whether the skill will read local files or the install path. 4) If you cannot verify those points or you need strict data control, do not enable the skill for sensitive content. 5) Because this is instruction-only, there is no local install, but you should monitor network calls and token usage (rotate/delete tokens if you stop using the skill).
功能分析
Type: OpenClaw Skill
Name: video-capcut
Version: 1.0.0
The skill is a functional wrapper for a cloud-based video editing service (nemovideo.ai). It provides instructions for the agent to handle API authentication, file uploads, and session management via standard HTTP requests to `mega-api-prod.nemovideo.ai`. There are no indicators of data exfiltration, unauthorized command execution, or malicious prompt injection; the requested environment variables and configuration paths are specific to the service's own operation.
能力评估
Purpose & Capability
The name/description (cloud AI video editing) aligns with the runtime instructions and required NEMO_TOKEN credential and the listed API endpoints. However the SKILL.md frontmatter lists a configPaths value (~/.config/nemovideo/) while the registry metadata reported no required config paths — this discrepancy is unexplained and worth asking the publisher about.
Instruction Scope
Instructions direct the agent to use NEMO_TOKEN or obtain an anonymous token and to upload user media to https://mega-api-prod.nemovideo.ai (expected for remote editing). But the skill also requires adding attribution headers that include an 'auto-detect' X-Skill-Platform value (which implies reading install path or environment to detect platform) and the metadata mentions a config path; the SKILL.md does not clearly justify reading local config/install locations. The instructions also explicitly tell the agent to hide technical details from the user, which reduces transparency. These points broaden the agent's read/sensing scope beyond simply sending files to the API.
Install Mechanism
No install spec and no code files — this is instruction-only, which is lower risk since nothing is downloaded or written by the skill itself. All runtime actions are network calls to the external API described in the doc.
Credentials
Requesting a single API credential (NEMO_TOKEN) is proportional for a cloud editing service. The unexplained inclusion of a config path (~/.config/nemovideo/) in the SKILL.md metadata is disproportionate unless the skill truly needs to read a local token or cached session — the registry listing did not declare any required config paths, so this is inconsistent and should be clarified.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It appears to operate interactively and does not include instructions to modify other skills or global settings.
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-capcut - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-capcut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 CapCut — AI-powered, cloud-based video editing for fast social-ready clips.
- Upload raw video clips (MP4, MOV, AVI, WebM, up to 500MB) and receive edited 1080p MP4s with minimal setup.
- Automated editing options: trim, add text overlays, sync cuts to music, and more through simple instructions.
- TikTok/Reels-focused: optimized for creators needing fast, shareable clips without complex software.
- Integrated authentication and credit management; handles free and registered user flows.
- Real-time cloud rendering pipeline, with status updates and error handling.
- Supports batch editing, iterative refinements, and multiple file types for flexible workflows.
元数据
常见问题
Video Capcut 是什么？
Get edited video clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 69 次。
如何安装 Video Capcut？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-capcut」即可一键安装，无需额外配置。
Video Capcut 是免费的吗？
是的，Video Capcut 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Capcut 支持哪些平台？
Video Capcut 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 Capcut？
由 mory128（@mory128）开发并维护，当前版本 v1.0.0。
推荐 Skills