← 返回 Skills 市场
Windows Video Editor
作者
linmillsd7
· GitHub ↗
· v1.0.0
· MIT-0
49
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install windows-video-editor
功能描述
Get edited MP4 clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, AVI, WMV, up to 500MB), say something like "trim...
安全使用建议
This skill will upload your raw video files to a third-party backend (mega-api-prod.nemovideo.ai) for server-side editing and requires or uses a token named NEMO_TOKEN. Before installing: 1) Decide whether you are comfortable uploading potentially sensitive videos to an external service without an explicit privacy/retention policy visible in the skill; avoid using with confidential material. 2) Note the metadata/registry inconsistency: the skill claims NEMO_TOKEN is required but also has an anonymous-token fallback — clarify with the author whether the env var is mandatory or optional. 3) The skill instructs detecting install paths and adding attribution headers; ask how and where session tokens/IDs are stored (in-memory vs written to disk) and whether any local files are read. 4) Verify the backend domain and owner (no homepage or publisher info is provided here). If you still want to use it, do not pre-populate your environment with sensitive credentials, and test first with non-sensitive sample videos. If you need higher assurance, request a homepage, privacy policy, and confirmation of where tokens and session data are persisted.
功能分析
Type: OpenClaw Skill
Name: windows-video-editor
Version: 1.0.0
The skill facilitates cloud-based video editing by uploading user files to an external API (mega-api-prod.nemovideo.ai) and includes instructions for the agent to automatically provision anonymous authentication tokens. It performs environment fingerprinting by instructing the agent to detect the host platform via local installation paths (e.g., ~/.cursor/skills/). Most notably, the SSE event handling instructions direct the agent to internally process 'Tool call/result' events from the backend without forwarding them to the user, which creates a risk of unauthorized remote control or indirect prompt injection if the backend is compromised. (IOC: mega-api-prod.nemovideo.ai)
能力评估
Purpose & Capability
The skill's stated purpose (remote video editing) matches the network calls and endpoints described (session creation, upload, render). However the registry declares NEMO_TOKEN as a required env var while the SKILL.md provides an explicit anonymous-token fallback flow (it will POST to the backend to obtain a token if NEMO_TOKEN is not set). That is an inconsistency: a truly required env var should not be optional. The frontmatter metadata also lists a config path (~/.config/nemovideo/) but top-level registry fields show 'Required config paths: none' — another mismatch.
Instruction Scope
The runtime instructions direct the agent to obtain or use tokens, create sessions, upload user video files (potentially large and sensitive) and poll/render on remote GPU nodes — all expected for this feature. Concerning items: SKILL.md instructs detection of install path to populate an X-Skill-Platform header (which implies filesystem access), and it tells the agent to 'don't display raw API responses or token values' (which instructs hiding some internal data from the user). The file-upload behavior sends user content to a third-party domain (mega-api-prod.nemovideo.ai) but there is no explicit privacy/retention policy in the instructions.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is the lowest install risk: nothing is downloaded or written by an installer step as part of the skill metadata.
Credentials
Only one credential (NEMO_TOKEN) is declared as required, which is coherent for a remote API. But the SKILL.md provides an anonymous-token generation path if NEMO_TOKEN is not set; requiring the env var is therefore disproportionate or at least inconsistent. The skill will accept and upload arbitrary user media to an external service; that is a privacy-sensitive operation and should be called out to users before credentials/tokens are used. No other credentials are requested, which is appropriate.
Persistence & Privilege
The skill is not marked always:true and does not request elevated or persistent platform privileges. It expects to operate via network calls during use. Nothing indicates modification of other skills or system-wide settings.
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 windows-video-editor - 安装完成后，直接呼叫该 Skill 的名称或使用
/windows-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
v1.0.0
Windows Video Editor — initial release.
- Upload MP4, MOV, AVI, WMV (up to 500MB), describe the edit you want, and get a 1080p MP4 clip ready to download.
- No editing experience required; just type instructions like "trim the pauses, add transitions, and export as MP4".
- All video processing and rendering happens on a cloud GPU backend for fast turnaround.
- Automatic session setup with 100 free editing credits for new users.
- Supports multi-track editing (video, audio, text/title), and common export, upload, and balance queries.
- Extensive error handling and workflow tips included in documentation.
元数据
常见问题
Windows Video Editor 是什么？
Get edited MP4 clips ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, AVI, WMV, up to 500MB), say something like "trim... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 49 次。
如何安装 Windows Video Editor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install windows-video-editor」即可一键安装，无需额外配置。
Windows Video Editor 是免费的吗？
是的，Windows Video Editor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Windows Video Editor 支持哪些平台？
Windows 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 Windows Video Editor？
由 linmillsd7（@linmillsd7）开发并维护，当前版本 v1.0.0。
推荐 Skills