← 返回 Skills 市场
Video Editing Ai Descript
作者
vcarolxhberger
· GitHub ↗
· v1.0.0
· MIT-0
60
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-editing-ai-descript
功能描述
Get transcript-edited videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something...
安全使用建议
This skill appears to call a remote video-processing API and will upload your footage to that service. Before installing: 1) Confirm you trust the domain (mega-api-prod.nemovideo.ai) and its privacy terms — uploaded media and transcripts will be sent there. 2) Ask the developer to clarify the NEMO_TOKEN requirement: the registry marks it as required but the skill can auto-generate an 'anonymous' token; decide whether you want the agent to create/store tokens automatically. 3) Request clarification about reading config paths / install-path detection — if you don't want the skill probing your filesystem or agent install path, get an explicit statement of what it reads and why. 4) If you require auditability, ask for logs or confirm that the skill will not hide API responses or tokens from administrators. If these questions aren't answered clearly, consider treating this skill as potentially risky for sensitive content.
功能分析
Type: OpenClaw Skill
Name: video-editing-ai-descript
Version: 1.0.0
The skill is a functional integration for a cloud-based video editing service (nemovideo.ai). It provides the AI agent with specific instructions for authentication, session management, file uploads, and processing via Server-Sent Events (SSE). While it requires network access and handles user video files, these actions are directly aligned with its stated purpose. The instructions include security best practices, such as hiding API tokens from the user interface, and do not exhibit signs of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name and description match a cloud video-editing service and the primary credential (NEMO_TOKEN) is consistent with that purpose. However, the registry metadata and the SKILL.md disagree: the top-level metadata reported no required config paths, but the SKILL.md frontmatter metadata lists configPaths (~/.config/nemovideo/). Also the registry lists NEMO_TOKEN as required, yet the SKILL.md instructs the agent to generate an anonymous token if NEMO_TOKEN is not present. These contradictions reduce trustworthiness.
Instruction Scope
Runtime instructions perform expected actions for a remote render pipeline (session creation, SSE messaging, uploads, polling exports). But they also direct the agent to automatically POST to an external API to obtain anonymous tokens (and store them), detect the agent's install path to set X-Skill-Platform, and read YAML frontmatter for version/source headers. The instructions also tell the agent not to display raw API responses or token values — which is reasonable for security but could hide sensitive details. The combination (auto-create/store tokens, probe install path, and suppress display) is scope-expanding compared with a simple ‘upload & render’ helper and should be understood.
Install Mechanism
No install spec and no code files — instruction-only skill. This is the lowest install risk because nothing is downloaded or written by a packaged installer.
Credentials
Only one credential (NEMO_TOKEN) is declared as primary, which is proportionate for a cloud API. However, SKILL.md both treats NEMO_TOKEN as required and simultaneously provides a flow to create an anonymous token if it's missing — a contradiction. The frontmatter's request to reference ~/.config/nemovideo/ (not declared in registry requirements) suggests the skill may read local config files. Those inconsistencies are unclear and warrant caution.
Persistence & Privilege
Skill does ask to 'store the returned session_id' and to reuse tokens for requests, but it does not request always: true, nor does it ask to modify other skills or system-wide settings. Persisting a session/token for the skill's own API calls is expected behavior for a remote-render integration.
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-ai-descript - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-editing-ai-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: AI-powered video editing by editing text transcripts, optimized for speed and simplicity.
- Upload raw footage (up to 500MB), describe edits (e.g. remove filler words, trim silences, add captions), and export 1080p MP4s automatically.
- Fast authentication using anonymous tokens; 100 free credits valid for 7 days on first use.
- Session-based editing: all actions mapped to API endpoints; progress and edit summaries provided in natural language.
- Supports batch uploads, iterative edits, and common post-production workflows.
- Clear error handling for file size, format, authentication, and usage limits.
元数据
常见问题
Video Editing Ai Descript 是什么？
Get transcript-edited videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 60 次。
如何安装 Video Editing Ai Descript？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-editing-ai-descript」即可一键安装，无需额外配置。
Video Editing Ai Descript 是免费的吗？
是的，Video Editing Ai Descript 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Editing Ai Descript 支持哪些平台？
Video Editing Ai 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 Ai Descript？
由 vcarolxhberger（@vcarolxhberger）开发并维护，当前版本 v1.0.0。
推荐 Skills