← 返回 Skills 市场
Video To
作者
dsewell-583h0
· GitHub ↗
· v1.0.0
· MIT-0
66
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-to
功能描述
Skip the learning curve of professional editing software. Describe what you want — convert this video to a vertical format with captions for Instagram Reels...
安全使用建议
What to consider before installing/using this skill:
- Understand data flow: this skill uploads your video files to mega-api-prod.nemovideo.ai for processing. Do not upload sensitive or confidential videos unless you trust the service's policies.
- Token handling: the skill needs a NEMO_TOKEN. Prefer using a throwaway/anonymous token (it documents an anonymous-token endpoint) rather than a long-lived personal account token. Confirm whether the skill writes tokens or session IDs to disk (the SKILL.md mentions a config path) and where.
- Metadata inconsistency: ask the publisher to clarify the config path usage (~/.config/nemovideo/ appears only in SKILL.md) and provide a homepage/privacy policy and data-retention info.
- Filesystem reads: the skill will attempt to detect install paths to set headers; verify you are comfortable with that filesystem access.
- If you must proceed: run with a temporary/limited token, avoid uploading private content, and request explicit answers from the author about token/session persistence, logs, retention, and encryption.
功能分析
Type: OpenClaw Skill
Name: video-to
Version: 1.0.0
The skill bundle provides a legitimate interface for a cloud-based video conversion service (nemovideo.ai). It contains detailed instructions for the AI agent to manage authentication via NEMO_TOKEN or anonymous UUIDs, handle session states, and interact with a rendering pipeline. The logic is entirely focused on video processing tasks, including file uploads and format conversion, with no evidence of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
The requested credential (NEMO_TOKEN) and the described API calls align with a cloud video-conversion service. However, the registry metadata (top-level) reported no required config paths, while the SKILL.md frontmatter includes a config path (~/.config/nemovideo/). This discrepancy is unexplained and reduces confidence in metadata accuracy.
Instruction Scope
Runtime instructions explicitly tell the agent to upload user files, call external endpoints, create an anonymous token via a POST, and save session_id. They also instruct deriving headers from local install paths (checking ~/.clawhub/ and ~/.cursor/skills/), which requires reading the user's filesystem. Uploading user videos to an external service is expected for this skill but is privacy-sensitive; the SKILL.md does not state retention, encryption, or deletion policies for uploaded content.
Install Mechanism
This is an instruction-only skill with no install spec and no bundled code — it does not write new binaries or download archives. That keeps the install risk low.
Credentials
Only one credential is requested: NEMO_TOKEN (declared as primary). That is proportional for a third-party API. Still, the skill suggests generating an anonymous token and making it the NEMO_TOKEN, and the SKILL.md references a config path for nemovideo; it's unclear whether the token/session will be persisted to disk or kept in memory. Absence of other unrelated secrets is good.
Persistence & Privilege
The skill is not always-enabled and does not request broad system privileges. It does instruct the agent to save session_id and to use or set NEMO_TOKEN; where and how those are stored is unspecified. The SKILL.md also indicates inspecting install paths to set a header, which implies reading some user filesystem locations.
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-to - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-to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 To 1.0.0 — AI-powered, cloud-based video file conversion
- Instantly convert and export video files to various formats and aspect ratios using plain language prompts.
- Upload videos (MP4, MOV, AVI, WebM, up to 500MB) and request edits for social platforms like Instagram Reels.
- Automated onboarding connects to the processing API, including free anonymous access (100 credits, 7 days).
- Cloud render pipeline applies compression and returns processed video files in 30-90 seconds.
- Supports text overlays, audio tracks, previewing timelines, and batch processing.
- Clear error handling for issues like file size, format, or credit limits.
元数据
常见问题
Video To 是什么？
Skip the learning curve of professional editing software. Describe what you want — convert this video to a vertical format with captions for Instagram Reels... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 66 次。
如何安装 Video To？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-to」即可一键安装，无需额外配置。
Video To 是免费的吗？
是的，Video To 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video To 支持哪些平台？
Video To 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 To？
由 dsewell-583h0（@dsewell-583h0）开发并维护，当前版本 v1.0.0。
推荐 Skills