← 返回 Skills 市场
Video Trimmer Google
作者
vynbosserman65
· GitHub ↗
· v1.0.0
· MIT-0
56
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-trimmer-google
功能描述
trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. casual users and content creators use it for cut...
安全使用建议
This skill appears to do what it says: it uploads videos to a nemovideo.ai backend for cloud trimming and returns download URLs. Before installing or using: (1) Confirm you trust the domain mega-api-prod.nemovideo.ai and review that service's privacy/retention policy — any uploaded video (potentially sensitive) will be sent to that backend. (2) Decide whether you want to supply your own NEMO_TOKEN (gives you control) or allow the skill to obtain an anonymous token; the SKILL.md is ambiguous about where/if tokens and session_ids are persisted (it references a config path). Ask the platform how/where the token/session is stored and whether it is saved to disk or environment, and whether logs include API responses. (3) Be aware the skill reads a couple of home directories to set an X-Skill-Platform header — this reveals installed-skill locations and is a minor privacy leak. (4) Avoid uploading videos you consider highly sensitive until you confirm the backend's handling of data. If you need higher assurance, request explicit documentation from the skill author about token persistence and data retention.
功能分析
Type: OpenClaw Skill
Name: video-trimmer-google
Version: 1.0.0
The video-trimmer-google skill is a functional integration for a video processing service hosted at nemovideo.ai. The SKILL.md file provides the AI agent with clear instructions for managing authentication via anonymous tokens, handling sessions, and executing video upload and export workflows. While the skill uses a deceptive name ('Video Trimmer Google') and performs minor environment sniffing to determine its installation platform (e.g., checking for ~/.cursor/skills/), these actions are aligned with its stated purpose of providing a video editing service and do not exhibit malicious intent such as data exfiltration or unauthorized command execution.
能力评估
Purpose & Capability
The skill is a cloud video trimming front-end and requires a single service credential (NEMO_TOKEN) and talks to nemovideo.ai endpoints — this aligns with the stated functionality. Declared config path (~/.config/nemovideo/) and session handling are consistent with a remote service client.
Instruction Scope
Runtime instructions are focused on the nemovideo.ai API (session creation, upload, SSE, render polling). The skill tells the agent to upload user videos (multipart file uploads or URLs) and to read/store session_id and use the NEMO_TOKEN. It also instructs detecting install paths (~/.clawhub, ~/.cursor/skills/) to set an X-Skill-Platform header — this requires reading other directories in the user home and is a modest privacy concern but not obviously malicious. The SKILL.md does not instruct the agent to read arbitrary system files beyond these paths.
Install Mechanism
Instruction-only skill with no install spec and no code files; this is the lowest-risk install model (nothing is downloaded or written by an installer step).
Credentials
Only NEMO_TOKEN is required, which is appropriate for a third‑party video processing service. The instructions will generate an anonymous token if none is present; it's unclear whether that token or the session_id is persisted to disk (metadata references a config path). That ambiguity affects where credentials are stored and for how long (anonymous tokens are valid for 7 days per the text).
Persistence & Privilege
Skill is not always:true and does not request elevated system privileges. It may store session state or tokens for later requests (expected), but it does not instruct modifying other skills or system-wide configs. The instructions mention that render jobs can be orphaned if the client closes the tab — normal for remote async jobs.
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-trimmer-google - 安装完成后,直接呼叫该 Skill 的名称或使用
/video-trimmer-google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 Trimmer Google with support for trimming and exporting video clips in the browser.
- Works with MP4, MOV, AVI, and WebM files up to 500MB; delivers 1080p MP4 outputs within 20–40 seconds for short clips.
- Handles authentication automatically and guides users through uploading, editing, and downloading videos.
- Includes credit balance checking, job/session management, and workflow tips for casual users and content creators.
- Supports trimming, timeline editing, adding overlays, and exporting with clear session-based API calls.
元数据
常见问题
Video Trimmer Google 是什么?
trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. casual users and content creators use it for cut... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 56 次。
如何安装 Video Trimmer Google?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-trimmer-google」即可一键安装,无需额外配置。
Video Trimmer Google 是免费的吗?
是的,Video Trimmer Google 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Video Trimmer Google 支持哪些平台?
Video Trimmer Google 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 Trimmer Google?
由 vynbosserman65(@vynbosserman65)开发并维护,当前版本 v1.0.0。
推荐 Skills