← 返回 Skills 市场
Video Editing With Descript
作者
whitejohnk-26
· GitHub ↗
· v1.0.0
· MIT-0
101
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-editing-with-descript
功能描述
Turn a 10-minute interview recording in MP4 into 1080p edited captioned videos just by typing what you need. Whether it's editing video by deleting words fro...
安全使用建议
This skill will upload your videos and transcripts to a third-party service (mega-api-prod.nemovideo.ai) and will create/use a NEMO_TOKEN (it can request an anonymous token automatically). Important considerations: (1) The skill’s name advertises “Descript” but the backend is nemovideo.ai — if you expected official Descript integration, do not assume this is the same service. (2) Your media and derived text will be sent off-device; review nemovideo.ai’s privacy/TOS before sending sensitive content. (3) You can supply your own NEMO_TOKEN if you want control over authentication; otherwise the skill may generate a short-lived anonymous token tied to a client UUID. (4) Ask the publisher for clarification about the Descript naming, the config path (~/.config/nemovideo/), and whether any logs or tokens are stored persistently. If you’re uncomfortable with third-party uploads or trademark/branding mismatch, do not install or use the skill until the author clarifies.
功能分析
Type: OpenClaw Skill
Name: video-editing-with-descript
Version: 1.0.0
The skill provides video editing capabilities by interfacing with the NemoVideo AI API (mega-api-prod.nemovideo.ai). The SKILL.md file contains detailed, functional instructions for the AI agent to manage authentication via anonymous tokens, handle multipart file uploads, and process asynchronous video rendering tasks. While the skill uses the 'Descript' brand name in its title despite utilizing a different backend (NemoVideo), the logic is transparently focused on its stated purpose and does not exhibit signs of data exfiltration, unauthorized command execution, or malicious prompt injection.
能力评估
Purpose & Capability
The name/description claim “with Descript” but every runtime instruction and API endpoint references mega-api-prod.nemovideo.ai (NEMO). That suggests either trademark mislabeling/impersonation or the skill does not implement what it advertises. Requiring a NEMO_TOKEN is coherent for a nemo backend, but not for a skill that truly integrates with Descript.
Instruction Scope
The SKILL.md instructs the agent to (a) check for NEMO_TOKEN, (b) call an anonymous-token endpoint to create a token if missing, (c) create a session, and (d) upload user files (multipart path or URL) to the remote service. Uploading user videos to a third-party cloud is expected for this purpose, but the skill will contact an external API and may create tokens autonomously — users should be aware that their media and derived transcripts go to nemovideo.ai. The SKILL.md also instructs platform detection via install path (~/.clawhub/, ~/.cursor/skills/) which implies the agent will probe local paths for header construction.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk by an installer here. That reduces the surface area for supply-chain risk.
Credentials
Only NEMO_TOKEN is declared as required (primaryEnv), which is proportional for a cloud editing service that requires authentication. However, the SKILL.md indicates it can obtain an anonymous NEMO_TOKEN itself via an API call if one is not present, and the YAML frontmatter mentions a config path (~/.config/nemovideo/) that is not reflected in the registry summary — this mismatch is inconsistent and worth clarifying.
Persistence & Privilege
The skill is not always-enabled and does not request elevated system privileges. It does instruct keeping a session_id for operations, but there is no instruction to persist or modify other skills or global agent config.
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-editing-with-descript - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-editing-with-descript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 Editing with Descript — Edit Video by Editing Text".
- Transcribe and edit videos by typing instructions; delete words from transcripts to cut footage.
- Automatic setup with token creation and cloud session management—user only uploads and types instructions.
- Single command workflows: remove filler words, add captions, trim silences, and export 1080p MP4—no manual timeline needed.
- Supports uploads up to 500MB in common video formats, with 1-2 minute processing time per clip.
- Exposes core actions (upload, edit, export, check credits/status) and robust error handling for seamless user experience.
元数据
常见问题
Video Editing With Descript 是什么？
Turn a 10-minute interview recording in MP4 into 1080p edited captioned videos just by typing what you need. Whether it's editing video by deleting words fro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 101 次。
如何安装 Video Editing With Descript？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-editing-with-descript」即可一键安装，无需额外配置。
Video Editing With Descript 是免费的吗？
是的，Video Editing With Descript 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Editing With Descript 支持哪些平台？
Video Editing With Descript 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 Editing With Descript？
由 whitejohnk-26（@whitejohnk-26）开发并维护，当前版本 v1.0.0。
推荐 Skills