← 返回 Skills 市场
Vertical Video Editor
作者
peandrover adam
· GitHub ↗
· v1.0.2
· MIT-0
154
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install vertical-video-editor
功能描述
Drop a video and describe what you need — this vertical-video-editor skill transforms horizontal or square footage into polished 9:16 content ready for TikTo...
安全使用建议
This skill will send your video files to nemovideo's cloud API for processing and will create a small file at ~/.config/nemovideo/client_id containing a UUID. Before installing, review NemoVideo's privacy and retention policy (what they keep and for how long), confirm you are comfortable uploading the kinds of videos you plan to process (avoid sensitive or private footage), and decide whether to supply your own NEMO_TOKEN or let the skill obtain a temporary anonymous token (anonymous tokens have limited lifetime/credits). If you want tighter control, disable autonomous skill invocation in your agent settings so uploads happen only after you explicitly confirm them, and verify the skill's homepage/repository to ensure the service is legitimate.
功能分析
Type: OpenClaw Skill
Name: vertical-video-editor
Version: 1.0.2
The vertical-video-editor skill is designed to interface with the NemoVideo cloud API for automated video reframing. It manages session state and authentication by generating a client ID in `~/.config/nemovideo/` and requesting anonymous tokens from `mega-api-prod.nemovideo.ai`. While it performs network requests and file uploads, these actions are explicitly documented and necessary for the stated purpose of cloud-based video processing. No evidence of data exfiltration, unauthorized access to sensitive local files, or malicious prompt injection was found.
能力评估
Purpose & Capability
The skill says it will reframe/crop/video-process and all declared requirements match that: primaryEnv=NEMO_TOKEN and a config path (~/.config/nemovideo/) are used for client_id and tokens. API endpoints, upload, SSE, and export behavior are consistent with a cloud-based video processing service.
Instruction Scope
SKILL.md instructs the agent to check NEMO_TOKEN, create/read ~/.config/nemovideo/client_id (UUID), obtain an anonymous token if needed, create a session, upload files (multipart or URL), and stream SSE responses. All these actions are within the expected scope for a remote video processing skill; it does not instruct reading unrelated files or exfiltrating data outside the NemoVideo endpoints.
Install Mechanism
There is no install spec and no code files — this is instruction-only. That is the lowest-risk install profile: nothing is downloaded or written beyond the small client_id file the skill itself instructs to create.
Credentials
Only one credential is declared (NEMO_TOKEN) and that directly maps to the API-based functionality. The skill will generate an anonymous token if NEMO_TOKEN is absent and stores only a UUID in ~/.config/nemovideo/client_id; no unrelated credentials or broad environment access are requested.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges. It writes a single client_id file under its own config path and uses API sessions. Autonomous model invocation is allowed by default (platform behavior) but is not combined with elevated privileges or other skills' config access.
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 vertical-video-editor - 安装完成后，直接呼叫该 Skill 的名称或使用
/vertical-video-editor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
v1.0.2
- Updated skill description for clarity and brevity, highlighting drag-and-drop workflow and supported formats.
- Added a step-by-step onboarding and authentication guide, including automatic anonymous token acquisition and session creation.
- Introduced detailed API request/response handling, including explicit mappings from backend GUI actions to API calls.
- Clarified routing logic for user requests (e.g., export, credits, upload) with a new summary table.
- Expanded error handling instructions and provided concrete sample payloads for all major actions.
- Adjusted branding and tone for user-friendliness while retaining guidance for advanced integrations.
v1.0.1
- Added homepage and repository links to the skill metadata.
- No core functionality changes; documentation updated only.
v1.0.0
Vertical Video Editor 1.0.0 — Initial Release
- Launch of AI-powered 9:16 vertical video editing optimized for TikTok, Instagram Reels, YouTube Shorts, and Snapchat.
- Smart horizontal-to-vertical conversion with face and action tracking for intelligent reframing.
- Native vertical-first editing tools: text overlays, animated captions, and platform-specific safe zones to avoid UI conflicts.
- Platform-specific export presets and safe zone adjustments for multi-platform publishing from one edit.
- Special features for talking-head content, vertical event highlights, and mobile-optimized transitions and captions.
元数据
常见问题
Vertical Video Editor 是什么？
Drop a video and describe what you need — this vertical-video-editor skill transforms horizontal or square footage into polished 9:16 content ready for TikTo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 154 次。
如何安装 Vertical Video Editor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vertical-video-editor」即可一键安装，无需额外配置。
Vertical Video Editor 是免费的吗？
是的，Vertical Video Editor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Vertical Video Editor 支持哪些平台？
Vertical Video Editor 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 Vertical Video Editor？
由 peandrover adam（@peand-rover）开发并维护，当前版本 v1.0.2。
推荐 Skills