← 返回 Skills 市场
Text To Video Editing
作者
mhogan2013-9
· GitHub ↗
· v1.0.0
· MIT-0
71
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install text-to-video-editing
功能描述
Skip the learning curve of professional editing software. Describe what you want — cut the pauses, add a title card at the start, and put captions throughout...
安全使用建议
This skill appears to do what it promises (upload video to a cloud API, run text-driven edits, return MP4s), but take these precautions before installing: 1) The skill will upload your video files to mega-api-prod.nemovideo.ai — only use it with non-sensitive footage unless you trust the service. 2) Supply your own NEMO_TOKEN only if you trust the provider; otherwise the skill will request an anonymous token automatically from the backend. 3) Clarify the apparent metadata mismatch: SKILL.md lists ~/.config/nemovideo/ as a config path while the registry said none. Ask the publisher for a homepage/privacy policy and verify the backend domain. 4) Test with a short, non-sensitive clip to confirm behavior and headers. If you need stronger assurance, ask for a published maintainer/homepage and a privacy/data-retention statement before using with real content.
功能分析
Type: OpenClaw Skill
Name: text-to-video-editing
Version: 1.0.0
The skill facilitates video editing by uploading user files and sending instructions to an external API (mega-api-prod.nemovideo.ai). It includes high-risk behaviors such as automated file uploads (up to 500MB), session management via Bearer tokens (NEMO_TOKEN), and the generation of anonymous identifiers for authentication. While these actions are consistent with the stated purpose of cloud-based video processing, the inherent risks of data exfiltration to a third-party service and the requirement for external network access in SKILL.md warrant a suspicious classification.
能力评估
Purpose & Capability
The name/description match the runtime instructions: the skill uploads video to a cloud render API and returns edited MP4s. Required credential (NEMO_TOKEN) is appropriate for a cloud API. Inconsistency: the registry metadata at the top said no required config paths, but the SKILL.md YAML frontmatter lists a config path (~/.config/nemovideo/). Also the skill's source/homepage are unknown, so the backend domain (mega-api-prod.nemovideo.ai) cannot be confirmed as a reputable vendor from this package alone.
Instruction Scope
SKILL.md stays within editing scope (session creation, SSE chat, upload, export, poll). It explicitly instructs uploading user video files and polling for render results — expected for this purpose but sensitive (user media will be sent to an external service). It also instructs generating an anonymous token if NEMO_TOKEN is not present, and to include various custom headers (including detection of an install path) — the install-path detection is odd for an instruction-only skill but not dangerous by itself.
Install Mechanism
No install spec and no code files (instruction-only). This minimizes on-disk code risk; nothing will be downloaded or installed by the skill itself.
Credentials
Only a single credential (NEMO_TOKEN) is requested, which fits the stated cloud API usage. The skill will fallback to obtaining an anonymous token via the API if no token is provided; that behavior is reasonable but means the agent will make external network calls to acquire credentials automatically. The SKILL.md frontmatter also declares a config path (~/.config/nemovideo/), which was not listed in the registry summary — this mismatch should be clarified.
Persistence & Privilege
The skill does not request always:true, does not require system-wide changes, and (being instruction-only) doesn't persist code or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other high privileges.
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 text-to-video-editing - 安装完成后,直接呼叫该 Skill 的名称或使用
/text-to-video-editing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 the "Text to Video Editing" skill.
- Upload MP4, MOV, AVI, or WebM files up to 500 MB and edit videos by describing your desired changes in plain text.
- Automatic session and authentication management with support for both anonymous and token-based connections.
- Supports common editing actions: cutting pauses, adding titles, captions, and more via text instructions.
- Cloud-based editing pipeline delivers 1080p MP4 results in 1–2 minutes for most clips.
- Real-time processing status and robust error handling for supported formats and account issues.
元数据
常见问题
Text To Video Editing 是什么?
Skip the learning curve of professional editing software. Describe what you want — cut the pauses, add a title card at the start, and put captions throughout... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 71 次。
如何安装 Text To Video Editing?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install text-to-video-editing」即可一键安装,无需额外配置。
Text To Video Editing 是免费的吗?
是的,Text To Video Editing 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Text To Video Editing 支持哪些平台?
Text To Video Editing 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 Text To Video Editing?
由 mhogan2013-9(@mhogan2013-9)开发并维护,当前版本 v1.0.0。
推荐 Skills